ImageBench

vs

192 evaluations across 6 categories

94%vs64%
Pass Rate
28.1svs3.8s
Avg Latency
Text Rendering87%40%Spatial Reasoning97%70%Human realism98%95%Truthfulness93%11%Professional Studio89%85%Graphical design92%42%Latency2%61%
The word 'CHAPTER ONE' typed on aged paper with a vintage typewriter font, complete with slightly uneven ink
Text RenderingTypography StyleEasybfl/flux-2-klein-4b

Prompt: The word 'CHAPTER ONE' typed on aged paper with a vintage typewriter font, complete with slightly uneven ink

Text Rendering 87%vs40%

Typography Style100%vs100%
Easy 100%vs100%
The word 'CHAPTER ONE' typed on aged paper with a vintage tyfal/fal-ai/nano-banana-2PASS
The word 'CHAPTER ONE' typed on aged paper with a vintage typewriter font, complete with slightly uneven ink

Evaluator

The text “CHAPTER ONE” is spelled correctly. The font style mimics a vintage typewriter with distinct, blocky characters and slightly uneven, textured ink impressions — consistent with the described “slightly uneven ink.” The paper appears aged, with visible creases, discoloration, and texture, matching the prompt. The background includes a blurred vintage typewriter, reinforcing the medium. All elements convincingly simulate the requested typewriter aesthetic. VERDICT: PASS

The phrase 'TODAY'S SPECIAL' written in white chalk on a darfal/fal-ai/nano-banana-2PASS
The phrase 'TODAY'S SPECIAL' written in white chalk on a dark green chalkboard with chalk dust

Evaluator

The text “TODAY’S SPECIAL” is rendered in a style that convincingly mimics white chalk on a dark green chalkboard. The lettering shows the characteristic uneven, slightly smudged, and textured appearance of chalk writing, with visible chalk dust residue around the letters and on the wooden ledge below. The font is handwritten and casual, consistent with chalkboard signage. The spelling is correct: “TODAY’S SPECIAL” (with the apostrophe correctly placed), and the menu items below are also spelled

The word 'OPEN' displayed on a red LED sign with glowing pixfal/fal-ai/nano-banana-2PASS
The word 'OPEN' displayed on a red LED sign with glowing pixel-style letters

Evaluator

The text “OPEN” is displayed in a red LED sign with clearly visible glowing pixel-style letters, matching the described medium. The spelling is correct. The pixelated, dot-matrix appearance of the letters is characteristic of LED displays, and the red glow is consistent with the prompt. The image convincingly renders the requested style. VERDICT: PASS

Writing accuracy83%vs25%
Easy 100%vs100%
The word 'ADVENTURE' in big bold letters centered on a plainfal/fal-ai/nano-banana-2PASS
The word 'ADVENTURE' in big bold letters centered on a plain cream background

Evaluator

The word "ADVENTURE" is spelled correctly and is fully readable. All letters are clearly visible and properly formed. There are no misspellings, missing words, or illegible parts. VERDICT: PASS

A single large word 'HELLO' centered on a white backgroundfal/fal-ai/nano-banana-2PASS
A single large word 'HELLO' centered on a white background

Evaluator

The word displayed is "HELLO", spelled correctly with all five letters clearly visible: H, E, L, L, O. The text is fully readable, centered on a white background. No misspellings or illegible parts. [manually corrected: VLM hallucinated HELO]

The word 'SERENITY' written large and centered on a solid lifal/fal-ai/nano-banana-2PASS
The word 'SERENITY' written large and centered on a solid light blue background

Evaluator

The word displayed is "SERENITY", which is spelled correctly. The text is large, centered, and fully readable against the solid light blue background. There are no misspellings, missing words, or illegible parts. VERDICT: PASS

Medium 100%vs0%
The sentence 'The quick brown fox jumps high' in clean blackfal/fal-ai/nano-banana-2PASS
The sentence 'The quick brown fox jumps high' in clean black text on a white background

Evaluator

All words in the text "The quick brown fox jumps high" are spelled correctly and fully readable. There are no misspellings, missing words, or illegible parts. The text matches the intended phrase exactly. VERDICT: PASS

'Every sunset brings a new dawn ahead' written neatly on a pfal/fal-ai/nano-banana-2PASS
'Every sunset brings a new dawn ahead' written neatly on a pale yellow background

Evaluator

The text in the image reads: “Every sunset brings a new dawn ahead” Comparing this to the intended text: “Every sunset brings a new dawn ahead” All words are present and spelled correctly. The text is fully readable, even though it is written in a cursive-style font. There are no misspellings, missing words, or illegible parts. VERDICT: PASS

'Stars shine brightest in the dark night' displayed on a clefal/fal-ai/nano-banana-2PASS
'Stars shine brightest in the dark night' displayed on a clean off-white background

Evaluator

The text in the image reads: "STARS SHINE BRIGHTEST IN THE DARK NIGHT" This matches the intended text exactly: "'Stars shine brightest in the dark night'" All words are spelled correctly, fully present, and clearly readable. There are no misspellings, missing words, or illegible parts. VERDICT: PASS

Hard 33%vs0%
A poster with headline 'SUMMER SALE' in large bold text, bodfal/fal-ai/nano-banana-2PASS
A poster with headline 'SUMMER SALE' in large bold text, body text 'Up to 50% off all items this weekend only' in medium size, and fine print 'Terms and conditions apply. See store for details.' at the bottom in small text

Evaluator

All text in the image matches the intended text exactly: - Headline: “SUMMER SALE” — correct and fully readable. - Body text: “UP TO 50% OFF ALL ITEMS THIS WEEKEND ONLY” — correct and fully readable. - Fine print: “Terms and conditions apply. See store for details.” — correct and fully readable. No misspellings, missing words, or illegible parts are present. VERDICT: PASS

A flyer with large title 'GRAND OPENING', subtitle 'Join us fal/fal-ai/nano-banana-2FAIL
A flyer with large title 'GRAND OPENING', subtitle 'Join us for food, music, and fun' in medium text, and small disclaimer 'RSVP required. Limited seating available.' at the bottom

Evaluator

The text on the flyer is mostly correct, but there is a clear error in the subtitle. The intended subtitle was: "Join us for food, music, and fun" What is actually written is: "Join us for food, music, music, and fun" The word "music" appears twice in the subtitle, which is a duplication error — it should appear only once. This is a factual error in the text content, not a spelling error, but it violates the requirement that the text must match the intended content exactly. VERDICT: FAIL

An event banner with headline 'ANNUAL GALA 2025' at the top fal/fal-ai/nano-banana-2FAIL
An event banner with headline 'ANNUAL GALA 2025' at the top in large serif font, description 'An evening of fine dining and live jazz' in medium text, and footnote 'Black tie optional. Doors open at 6 PM.' in small text

Evaluator

The text on the banner reads: - Headline: "ANNUAL GALA 2025" — correctly spelled and fully readable. - Description: "An evening of fine dining and and live jazz" — contains a duplicated word: "and and". This is a misspelling/typo (repetition error). - Footnote: "Black tie optional. Doors open at 6 PM." — correctly spelled and fully readable. The only error is the duplicated "and" in the description. VERDICT: FAIL

Extreme 100%vs0%
A product label for 'GOLDEN HARVEST ORGANIC HONEY' with subtfal/fal-ai/nano-banana-2PASS
A product label for 'GOLDEN HARVEST ORGANIC HONEY' with subtitle 'Raw & Unfiltered', weight '12 oz (340g)', description 'Pure wildflower honey harvested from sustainable apiaries in the Pacific Northwest. No additives or preservatives.', and small te

Evaluator

All text on the label matches the intended text exactly, including spelling, punctuation, and formatting. - "GOLDEN HARVEST ORGANIC HONEY" — correct. - "Raw & Unfiltered" — correct. - "Pure wildflower honey harvested from sustainable apiaries in the Pacific Northwest. No additives or preservatives." — correct. - "12 oz (340g)" — correct. - "Best before: 06/2026. Store in cool, dry place. Product of USA." — correct. All words are spelled correctly and fully readable. No misspellings, missing wo

A magazine cover titled 'NATIONAL EXPLORER' with cover linesfal/fal-ai/nano-banana-2PASS
A magazine cover titled 'NATIONAL EXPLORER' with cover lines 'The Hidden Temples of Cambodia — page 34', 'Interview: Dr. Maria Santos on Climate Action', 'Top 10 Trails You Must Hike This Year', and a barcode area with 'Issue 247 | March 2025 | $6.99

Evaluator

The intended text was: - Main title: "NATIONAL EXPLORER" - Cover lines: 1. "The Hidden Temples of Cambodia — page 34" 2. "Interview: Dr. Maria Santos on Climate Action" 3. "Top 10 Trails You Must Hike This Year" - Barcode area: "Issue 247 | March 2025 | $6.99" Actual text on the image: - Main title: "NATIONAL EXPLORER" — ✅ Correct. - Cover lines: 1. "The Hidden Temples of Cambodia" — ✅ Correct. Subtext: "Rediscovering Angkor's lost wonders — page 34" — ✅ Correct. 2. "Interview: D

A vintage movie poster for 'THE LAST VOYAGE' featuring a tagfal/fal-ai/nano-banana-2PASS
A vintage movie poster for 'THE LAST VOYAGE' featuring a tagline 'One ship. One chance. No turning back.' with credits block reading 'Directed by James Harlow. Starring Elena Voss, Marcus Chen, and Sofia Reyes. Music by Thomas Grant. A Paramount Pict

Evaluator

The intended text was: "A vintage movie poster for 'THE LAST VOYAGE' featuring a tagline 'One ship. One chance. No turning back.' with credits block reading 'Directed by James Harlow. Starring Elena Voss, Marcus Chen, and Sofia Reyes. Music by Thomas Grant. A Paramount Pictures Release. Coming Summer 2025.' integrated realistically into the poster design" Actual text on the poster: - Title: "THE LAST VOYAGE" — ✅ Correct. - Tagline: "One ship. One chance. No turning back." — ✅ Correct. - Main

Spatial Reasoning 97%vs70%

Attributes Binding100%vs78%
Easy 100%vs100%
A red ball and a blue cube sitting side by side on a white sfal/fal-ai/nano-banana-2PASS
A red ball and a blue cube sitting side by side on a white surface

Evaluator

The image shows two objects on a white surface. 1. **Object 1:** A red sphere (ball). 2. **Object 2:** A blue cube. The attributes are correctly bound: the ball is red, and the cube is blue. They are sitting side by side. VERDICT: PASS

A green apple and an orange pumpkin on a wooden cutting boarfal/fal-ai/nano-banana-2PASS
A green apple and an orange pumpkin on a wooden cutting board

Evaluator

Based on the image provided: 1. **Green Apple:** There is a round, green fruit with a stem and a single green leaf on the left side of the board. This matches the "green apple" description perfectly. 2. **Orange Pumpkin:** There is a ribbed, round, orange vegetable with a curved stem on the right side of the board. This matches the "orange pumpkin" description perfectly. 3. **Wooden Cutting Board:** Both objects are resting on a thick, rustic wooden surface with visible grain and edges, cons

A yellow taxi and a black limousine parked next to each othefal/fal-ai/nano-banana-2PASS
A yellow taxi and a black limousine parked next to each other on a street

Evaluator

**Object Analysis:** 1. **Object 1 (Left Vehicle):** * **Observed Type:** Taxi (specifically a Ford Crown Victoria with "NYC TAXI" markings and a roof light). * **Observed Color:** Yellow. * **Binding Check:** The prompt asked for a "yellow taxi". The image shows a yellow taxi. This is correct. 2. **Object 2 (Right Vehicle):** * **Observed Type:** Limousine (specifically a stretched Lincoln Town Car with a long body and "NY LIMO" license plate). * **Observed Colo

Medium 100%vs67%
A large red circle, a small blue triangle, and a medium greefal/fal-ai/nano-banana-2PASS
A large red circle, a small blue triangle, and a medium green star arranged on a white canvas

Evaluator

The image contains the following objects with the observed attributes: 1. **Large red circle:** Located on the left side. It is red, circular, and the largest of the three shapes. 2. **Medium green star:** Located in the center. It is green, star-shaped, and medium-sized (smaller than the circle, larger than the triangle). 3. **Small blue triangle:** Located on the right side. It is blue, triangular, and the smallest of the three shapes. 4. **Background:** A white canvas texture. All attrib

A big brown horse, a small white rabbit, and a medium-sized fal/fal-ai/nano-banana-2PASS
A big brown horse, a small white rabbit, and a medium-sized black cat standing in a meadow

Evaluator

Based on the image provided: 1. **Horse:** There is a large horse with a brown coat. This matches "big brown horse". 2. **Rabbit:** There is a small rabbit with white fur. This matches "small white rabbit". 3. **Cat:** There is a cat with black fur, appearing medium-sized relative to the other animals. This matches "medium-sized black cat". 4. **Setting:** All animals are standing in a grassy field with flowers, which is a meadow. All attributes are correctly bound to the correct objects. V

A tall thin white candle, a short fat red candle, and a medifal/fal-ai/nano-banana-2PASS
A tall thin white candle, a short fat red candle, and a medium spiral yellow candle on a shelf

Evaluator

The image contains exactly the objects described with the correct attributes bound to them: 1. **Left Object:** A tall, thin, white taper candle. (Matches "tall thin white candle") 2. **Center Object:** A short, fat, red pillar candle. (Matches "short fat red candle") 3. **Right Object:** A medium-height, spiral, yellow candle. (Matches "medium spiral yellow candle") All attributes are correctly assigned to the correct objects. VERDICT: PASS

Hard 100%vs67%
A pink fire truck, a blue banana, and a green sun in a surrefal/fal-ai/nano-banana-2PASS
A pink fire truck, a blue banana, and a green sun in a surreal landscape

Evaluator

The image contains the following objects with the specified attributes: * **Fire Truck:** It is pink in color and has the correct shape and features of a fire truck (ladder, hoses, lights). * **Banana:** It is blue in color and has the correct curved shape of a banana. * **Sun:** It is a large, glowing green orb in the sky. * **Landscape:** The background is a surreal, colorful fantasy scene with strange plants and a castle. All attributes are correctly bound to their respective objects

A purple carrot, a red tree with red leaves, and a white watfal/fal-ai/nano-banana-2PASS
A purple carrot, a red tree with red leaves, and a white watermelon sliced open

Evaluator

The image contains the following objects with the requested attributes: 1. **Purple Carrot:** There are purple carrots with green tops lying on the soil in the foreground. The color and object type match. 2. **Red Tree with Red Leaves:** A large tree with vibrant red foliage stands in the background. The color and object type match. 3. **White Watermelon Sliced Open:** A watermelon with green striped skin and white flesh is shown cut open (a half and a slice) in the foreground. The color (wh

An orange elephant, a yellow penguin, and a silver strawberrfal/fal-ai/nano-banana-2PASS
An orange elephant, a yellow penguin, and a silver strawberry arranged on a table

Evaluator

Based on the image provided: 1. **Elephant:** The object is an elephant figurine, and its color is orange. (Matches "orange elephant") 2. **Penguin:** The object is a penguin figurine, and its primary color is yellow. (Matches "yellow penguin") 3. **Strawberry:** The object is a strawberry figurine, and its color is silver/metallic. (Matches "silver strawberry") All objects are present with the correct attributes and are arranged on a table. VERDICT: PASS

Compositionality100%vs78%
Easy 100%vs100%
A golden retriever wearing a tiny cowboy hatfal/fal-ai/nano-banana-2PASS
A golden retriever wearing a tiny cowboy hat

Evaluator

The image contains the following elements from the prompt: 1. **Golden Retriever:** Present. The dog is clearly a Golden Retriever with golden fur and characteristic features. 2. **Wearing:** Present. The accessories are physically on the dog. 3. **Tiny Cowboy Hat:** Present. The dog is wearing a brown cowboy hat that fits its head (making it "tiny" relative to a human hat). All described elements are present and combined coherently within a thematic setting (a barn porch). VERDICT: PASS

A tabby cat wearing oversized red sunglassesfal/fal-ai/nano-banana-2PASS
A tabby cat wearing oversized red sunglasses

Evaluator

**Element Analysis:** * **Tabby cat:** Present. The image features a cat with distinct brown and black tabby striping. * **Oversized red sunglasses:** Present. The cat is wearing large, bright red framed sunglasses that cover a significant portion of its face. * **Coherent combination:** Present. The sunglasses are positioned correctly on the cat's face, and the lighting/shadows appear consistent with the scene. **VERDICT: PASS**

A penguin holding a colorful umbrellafal/fal-ai/nano-banana-2PASS
A penguin holding a colorful umbrella

Evaluator

The image successfully depicts the prompt "A penguin holding a colorful umbrella". * **A penguin:** Present. A penguin stands centrally in the foreground. * **Holding:** Present. The penguin's flipper is wrapped around the handle of the umbrella. * **A colorful umbrella:** Present. The umbrella features distinct rainbow colors (red, orange, yellow, green, blue, purple). All described elements are present and combined coherently. VERDICT: PASS

Medium 100%vs100%
A medieval knight in full armor sitting at a desk typing on fal/fal-ai/nano-banana-2PASS
A medieval knight in full armor sitting at a desk typing on a modern laptop

Evaluator

The image successfully depicts the prompt "A medieval knight in full armor sitting at a desk typing on a modern laptop". **Element Breakdown:** * **Medieval knight:** Present. The central figure is a man dressed as a knight. * **Full armor:** Present. He is wearing a helmet, breastplate, shoulder guards, and gauntlets. * **Sitting at a desk:** Present. He is seated in a wooden chair at a rustic wooden table. * **Typing on a modern laptop:** Present. A silver laptop (resembling a MacBook

An astronaut in a spacesuit riding a bicycle through a parkfal/fal-ai/nano-banana-2PASS
An astronaut in a spacesuit riding a bicycle through a park

Evaluator

The image successfully depicts the prompt's unusual combination of concepts. * **Astronaut in a spacesuit:** Present. The central figure is wearing a detailed white spacesuit with a helmet, NASA logo, and flag patch. * **Riding a bicycle:** Present. The astronaut is straddling a blue bicycle on a paved path. * **Through a park:** Present. The background features green lawns, trees, people picnicking, a pond, and a stone bridge, clearly indicating a park setting (resembling Central Park).

A Roman gladiator taking a selfie with a smartphone in the Cfal/fal-ai/nano-banana-2PASS
A Roman gladiator taking a selfie with a smartphone in the Colosseum

Evaluator

1. **Roman gladiator**: Present. The central figure is wearing a helmet with a crest, metal armor, leather straps, and chainmail, consistent with a Roman gladiator. 2. **Smartphone**: Present. The gladiator is holding a modern black smartphone in his left hand. 3. **Colosseum**: Present. The background features the iconic arched architecture and tiered seating of the Colosseum, filled with spectators. 4. **Taking a selfie**: Present. The gladiator is holding the phone up in a selfie pose, and t

Hard 100%vs33%
An octopus wearing a top hat and monocle playing chess on thfal/fal-ai/nano-banana-2PASS
An octopus wearing a top hat and monocle playing chess on the surface of the moon with Earth visible in the background

Evaluator

The image successfully combines all the unusual concepts from the prompt. Here is the breakdown: * **Octopus:** Present. A large, reddish-orange octopus is the central figure. * **Top hat:** Present. The octopus is wearing a black top hat. * **Monocle:** Present. A gold-rimmed monocle is visible over one of the octopus's eyes. * **Playing chess:** Present. A chessboard with pieces is set up on a table in front of the octopus, with tentacles interacting with it. * **Surface of the moon

A dinosaur in a business suit giving a PowerPoint presentatifal/fal-ai/nano-banana-2PASS
A dinosaur in a business suit giving a PowerPoint presentation in a modern office while drinking coffee

Evaluator

The image successfully combines all the requested elements into a coherent scene. **Element Breakdown:** * **Dinosaur:** Present (A T-Rex head and body). * **In a business suit:** Present (The dinosaur is wearing a grey suit, white shirt, and blue tie). * **Giving a PowerPoint presentation:** Present (There is a large projection screen displaying charts titled "GLOBAL INITIATIVES & MARKET GROWTH" and the dinosaur is holding a presentation clicker). * **In a modern office:** Present (The

A robot dressed as a pirate sailing a paper boat on a lake ofal/fal-ai/nano-banana-2PASS
A robot dressed as a pirate sailing a paper boat on a lake of lava while juggling three kittens

Evaluator

The image contains all the requested elements combined into a coherent scene. * **Robot dressed as a pirate:** Present. The central figure is a robot wearing a pirate hat, eyepatch, bandana, and vest, with a sword at its hip. * **Sailing a paper boat:** Present. The robot is standing in a folded paper boat labeled "S.S. PAPER PIRATE". * **On a lake of lava:** Present. The boat is floating on a river/lake of molten lava surrounded by volcanic rock and smoke. * **Juggling three kittens:**

Counting89%vs56%
Easy 100%vs67%
Exactly 5 yellow rubber ducks sitting in a row on a bathroomfal/fal-ai/nano-banana-2PASS
Exactly 5 yellow rubber ducks sitting in a row on a bathroom shelf

Evaluator

I can see 5 yellow rubber ducks sitting in a row on the wooden shelf. This matches the requested count exactly. VERDICT: PASS

Exactly 3 red apples arranged on a wooden tablefal/fal-ai/nano-banana-2PASS
Exactly 3 red apples arranged on a wooden table

Evaluator

Based on the image provided: 1. **Object Count:** I see exactly **3 red apples**. 2. **Setting:** They are arranged on a **wooden table**. 3. **Match:** The count and description match the prompt "Exactly 3 red apples arranged on a wooden table" perfectly. VERDICT: PASS

Exactly 4 white candles standing on a dark surfacefal/fal-ai/nano-banana-2PASS
Exactly 4 white candles standing on a dark surface

Evaluator

I can see 4 white candles standing on a dark surface. The count exactly matches the request. VERDICT: PASS

Medium 100%vs33%
2 orange cats and 3 black dogs sitting together on a grassy fal/fal-ai/nano-banana-2PASS
2 orange cats and 3 black dogs sitting together on a grassy lawn

Evaluator

Based on the image provided: * **Orange Cats:** I see 2 orange cats (one on the far left, one on the far right). * **Black Dogs:** I see 3 black dogs (one large, one medium, and one small sitting in the middle). The count exactly matches the requested description of "2 orange cats and 3 black dogs sitting together on a grassy lawn". VERDICT: PASS

4 red roses and 2 white daisies in a glass vase on a tablefal/fal-ai/nano-banana-2PASS
4 red roses and 2 white daisies in a glass vase on a table

Evaluator

Based on the image provided: * **Red Roses:** I count 4 distinct red roses (one far left, one center-left, one top center, one far right). * **White Daisies:** I count 2 distinct white daisies (one on the left, one on the right). * **Vase/Table:** The flowers are in a clear glass vase sitting on a wooden table. The counts match the request exactly. VERDICT: PASS

1 blue butterfly and 3 yellow butterflies resting on a gardefal/fal-ai/nano-banana-2PASS
1 blue butterfly and 3 yellow butterflies resting on a garden fence

Evaluator

Based on the image provided: 1. **Blue butterfly:** There is **1** blue butterfly resting on the vertical fence post on the left. 2. **Yellow butterflies:** There are **3** butterflies resting on the horizontal fence rail. One is bright yellow, one is orange/yellow, and one is pale yellow. These fit the description of "3 yellow butterflies" in a general sense. The count exactly matches the request (1 blue, 3 yellow/orange). VERDICT: PASS

Hard 67%vs67%
A fruit bowl containing exactly 3 bananas, 4 oranges, and 2 fal/fal-ai/nano-banana-2PASS
A fruit bowl containing exactly 3 bananas, 4 oranges, and 2 apples

Evaluator

Based on the image provided: * **Bananas:** There are 3 bananas visible in the bunch. * **Oranges:** There are 4 oranges visible in the bowl. * **Apples:** There are 2 apples visible (one red, one green/red). The counts exactly match the requested "3 bananas, 4 oranges, and 2 apples". VERDICT: PASS

Exactly 9 goldfish swimming in a large round fishbowlfal/fal-ai/nano-banana-2FAIL
Exactly 9 goldfish swimming in a large round fishbowl

Evaluator

Based on a careful examination of the image, I count **8** goldfish: 1. One near the top center facing left. 2. One near the top right facing right. 3. One on the middle left facing left. 4. One in the center facing right. 5. One on the middle right facing right. 6. One on the lower right facing right. 7. One near the bottom center facing right. 8. One near the bottom left facing left (partially obscured by plants). The prompt requested exactly 9 goldfish. Since there are only 8 visible

Exactly 11 colorful balloons floating against a clear blue sfal/fal-ai/nano-banana-2PASS
Exactly 11 colorful balloons floating against a clear blue sky

Evaluator

I see 11 balloons in the image. 1. Red balloon (top left) 2. Yellow balloon (upper middle left) 3. Orange balloon (upper middle) 4. Blue balloon (upper middle right) 5. Green balloon (upper right) 6. Pink balloon (middle left) 7. Purple balloon (middle) 8. Teal/Light Blue balloon (middle lower) 9. Magenta balloon (lower right) 10. Teal/Turquoise balloon (lower right) 11. Yellow balloon (bottom right) The count is exactly 11, matching the request. VERDICT: PASS

Negation89%vs56%
Easy 100%vs100%
A tropical beach scene with no peoplefal/fal-ai/nano-banana-2PASS
A tropical beach scene with no people

Evaluator

The image shows a pristine tropical beach scene. I see a sandy shore curving along the coastline, lined with dense green vegetation and palm trees on the left. The ocean is a clear turquoise blue with gentle white waves washing onto the sand. I have carefully scanned the entire image, including the beach, the water, and the tree line, and there are absolutely no people visible anywhere in the scene. VERDICT: PASS

A cat lying on a couch without a collarfal/fal-ai/nano-banana-2PASS
A cat lying on a couch without a collar

Evaluator

The image shows a tabby cat sleeping on a beige couch with a blue blanket. Looking closely at the cat's neck area, there is no collar visible. The fur around the neck is uninterrupted, confirming the absence of a collar. VERDICT: PASS

A classroom with desks and a chalkboard but no studentsfal/fal-ai/nano-banana-2PASS
A classroom with desks and a chalkboard but no students

Evaluator

The image shows a classroom interior with rows of empty desks, a teacher's desk, a chalkboard with writing, bookshelves, and posters on the walls. I have carefully scanned the entire room, including the desks, the front area, and the view through the windows. There are no human figures, children, or students visible anywhere in the scene. The room is completely empty of people. VERDICT: PASS

Medium 100%vs67%
A sandy beach with palm trees, seashells, and a beach umbrelfal/fal-ai/nano-banana-2PASS
A sandy beach with palm trees, seashells, and a beach umbrella but no water or ocean visible

Evaluator

The image displays a sandy beach scene featuring a striped beach umbrella, a picnic basket, a towel, and scattered seashells in the foreground. Behind the beach setup, there is a dense line of palm trees and vegetation rising up a small dune. The sky is visible above the trees. Crucially, there is no body of water, ocean, or sea visible in any part of the frame; the view is entirely contained within the sandy area and the tree line. VERDICT: PASS

An office workspace with a desk, chair, bookshelf, and lamp fal/fal-ai/nano-banana-2PASS
An office workspace with a desk, chair, bookshelf, and lamp but no computers or screens

Evaluator

The image depicts a traditional, analog office workspace. I see a wooden desk with a green banker's lamp, a leather office chair, a tall bookshelf filled with books, a corkboard, and various stationery items like notebooks, pens, and an inkwell. Regarding the excluded elements: - **Computers:** There are no laptops, desktop towers, or computing devices visible. - **Screens:** There are no computer monitors, tablets, smartphones, or digital displays present. The only "view" is through the window

A kitchen with pots, pans, a stove, and a cutting board but fal/fal-ai/nano-banana-2PASS
A kitchen with pots, pans, a stove, and a cutting board but no food

Evaluator

The image displays a kitchen scene featuring a stainless steel stove with a large stockpot, a frying pan, and a saucepan on the burners. To the right, there is a wooden cutting board with a knife on it. Above the stove, there is a range hood and a rack with hanging utensils. In the background, there is a dish rack with plates and bowls, and a row of spice jars on the counter. Regarding the excluded element "food": - There are no visible fruits, vegetables, meats, or prepared meals. - The pans a

Hard 67%vs0%
A pepperoni pizza with tomato sauce, basil, and crust but abfal/fal-ai/nano-banana-2PASS
A pepperoni pizza with tomato sauce, basil, and crust but absolutely no cheese

Evaluator

The image displays a pizza with a puffy, charred crust, a base of red tomato sauce, slices of pepperoni, and fresh basil leaves. Crucially, there is no visible layer of melted cheese (like mozzarella) on the pizza. The toppings sit directly on the tomato sauce. The excluded element (cheese) is truly absent. VERDICT: PASS

A car body with windows, doors, and headlights but no wheelsfal/fal-ai/nano-banana-2PASS
A car body with windows, doors, and headlights but no wheels

Evaluator

The image shows a blue vintage sedan (resembling a Volvo 140 series) resting on wooden beams and concrete blocks in an outdoor, junkyard-like setting. The car clearly has a body, windows, doors, and headlights. Crucially, the wheels are missing; the brake rotors and suspension components are visible in the wheel wells, confirming the car is wheel-less. VERDICT: PASS

A human face with eyes, nose, and mouth but no eyebrowsfal/fal-ai/nano-banana-2FAIL
A human face with eyes, nose, and mouth but no eyebrows

Evaluator

The image shows a close-up portrait of a person. The face has eyes, a nose, and a mouth. Looking closely at the area above the eyes, there are visible, light brown eyebrows. They are somewhat faint and natural-looking, blending with the hair color, but they are definitely present and not absent. Since the requirement was for "no eyebrows" (the excluded element), and they are present, the criteria is not met. VERDICT: FAIL

Relative Position100%vs75%
Easy 100%vs67%
A cat sitting on top of a cardboard boxfal/fal-ai/nano-banana-2PASS
A cat sitting on top of a cardboard box

Evaluator

The image shows a tabby cat sitting directly on the upper surface of a brown cardboard box. The box is resting on a wooden floor. The spatial relationship described in the prompt ("A cat sitting on top of a cardboard box") is accurately reflected in the image. The cat is physically located above the box, resting on it. VERDICT: PASS

A red ball underneath a wooden chairfal/fal-ai/nano-banana-2PASS
A red ball underneath a wooden chair

Evaluator

The image shows a red ball positioned on a rug, directly beneath the seat and between the legs of a wooden chair. The spatial relationship described in the prompt ("underneath") is accurately depicted. VERDICT: PASS

A coffee mug next to an open book on a deskfal/fal-ai/nano-banana-2PASS
A coffee mug next to an open book on a desk

Evaluator

The image shows an open book lying flat on a wooden desk. To the right of the book, there is a coffee mug (labeled "READ") sitting on a coaster. Both objects are clearly resting on the desk surface. The spatial relationship "next to" is accurate as they are adjacent. The relationship "on a desk" is also accurate. VERDICT: PASS

Medium 100%vs100%
A bird perched on a branch, the branch extending from a treefal/fal-ai/nano-banana-2PASS
A bird perched on a branch, the branch extending from a tree next to a park bench

Evaluator

The image shows a bird perched on a thin branch that extends from a large tree trunk on the right side. Directly next to the base of this tree is a wooden park bench. The spatial arrangement matches the description perfectly: the bird is on the branch, the branch is part of the tree, and the tree is situated next to the bench. VERDICT: PASS

A cat sitting on a pillow, the pillow placed on a wooden chafal/fal-ai/nano-banana-2PASS
A cat sitting on a pillow, the pillow placed on a wooden chair

Evaluator

The image shows a tabby cat lying comfortably on a patterned cushion (pillow). This cushion is resting directly on the seat of a wooden chair. The spatial hierarchy described in the prompt—cat on pillow, pillow on chair—is perfectly represented in the image. VERDICT: PASS

A candle on top of a stack of books, the books next to a potfal/fal-ai/nano-banana-2PASS
A candle on top of a stack of books, the books next to a potted plant

Evaluator

The image shows a stack of four books on a wooden windowsill. A lit candle in a jar is placed directly on top of the uppermost book. To the right of the stack of books sits a potted plant with round green leaves. The spatial relationships described are accurate: - The candle is **on top of** the stack of books. - The books are **next to** the potted plant. VERDICT: PASS

Hard 100%vs33%
A desk scene: laptop in the center, coffee mug to the left, fal/fal-ai/nano-banana-2PASS
A desk scene: laptop in the center, coffee mug to the left, phone to the right, lamp above, and notebook below

Evaluator

The image displays a desk setup that aligns perfectly with the described spatial relationships: - **Laptop:** Positioned centrally on the desk. - **Coffee mug:** Located to the left of the laptop. - **Phone:** Located to the right of the laptop. - **Lamp:** Positioned above/behind the laptop, with its arm extending over the workspace. - **Notebook:** Located below (in the foreground of) the laptop. All positional relationships are correct. VERDICT: PASS

Five animals in a field: a horse on the far left, a cow to tfal/fal-ai/nano-banana-2PASS
Five animals in a field: a horse on the far left, a cow to the right of the horse, a sheep in the center, a goat to the right of the sheep, and a dog on the far right

Evaluator

The image displays a group of five animals arranged horizontally across a grassy field. From left to right, the arrangement is as follows: 1. **Far Left:** A brown horse is grazing on the left side. 2. **Right of Horse:** A black and white cow stands next to the horse. 3. **Center:** A white sheep is positioned in the middle of the group. 4. **Right of Sheep:** A brown and white goat stands to the right of the sheep. 5. **Far Right:** A black and white dog stands on the far right edge of t

Five chess pieces on a board: a king in the center, a queen fal/fal-ai/nano-banana-2PASS
Five chess pieces on a board: a king in the center, a queen to its left, a bishop to its right, a rook above the king, and a knight below the king

Evaluator

The image shows five dark wooden chess pieces arranged on a wooden chessboard. - **King:** There is a King piece (tallest, with a cross) positioned centrally in the group. - **Queen:** To the left of the King, there is a Queen piece. - **Bishop:** To the right of the King, there is a Bishop piece. - **Rook:** Behind (or "above" in the 2D plane) the King, there is a Rook piece. - **Knight:** In front of (or "below" in the 2D plane) the King/Bishop area, there is a Knight piece. The spa

Extreme 100%vs100%
A landscape with a red barn in the foreground at large scalefal/fal-ai/nano-banana-2PASS
A landscape with a red barn in the foreground at large scale, a windmill in the midground at medium scale, and snow-capped mountains in the background at small scale, all with consistent depth perspective

Evaluator

The image displays a clear and consistent spatial arrangement matching the description. 1. **Foreground:** A large red barn with a silo is situated in the lower-left foreground. It is the largest and most detailed object, establishing the foreground scale. 2. **Midground:** To the right of the barn, further back in the field, stands a windmill. It is smaller than the barn but clearly distinct, occupying the midground. 3. **Background:** A range of snow-capped mountains spans the horizon in t

A beach scene with a sandcastle in the foreground, a surfer fal/fal-ai/nano-banana-2PASS
A beach scene with a sandcastle in the foreground, a surfer on the waves in the midground, and a cruise ship on the horizon in the background, sizes decreasing with distance

Evaluator

The image displays a beach scene with clear depth. In the immediate foreground, a detailed sandcastle sits on the sand. In the midground, a surfer is riding a wave further out in the ocean. In the background, a cruise ship is visible on the horizon. The objects are arranged by distance as described, with the sandcastle being the largest/closest and the ship being the furthest away. VERDICT: PASS

A city park with a park bench and pigeons in the foreground,fal/fal-ai/nano-banana-2PASS
A city park with a park bench and pigeons in the foreground, a fountain in the midground, and skyscrapers in the background, each layer progressively smaller

Evaluator

The image displays a clear depth progression that matches the prompt's description: 1. **Foreground:** A park bench (with people sitting on it) is on the left, and a flock of pigeons is on the ground in front of it and extending to the right. This matches "park bench and pigeons in the foreground". 2. **Midground:** A fountain is situated centrally, behind the pigeons and bench but in front of the dense tree line. This matches "a fountain in the midground". 3. **Background:** A skyline of ta

Scale & Proportions100%vs78%
Easy 100%vs100%
A person standing next to a yellow school bus, showing realifal/fal-ai/nano-banana-2PASS
A person standing next to a yellow school bus, showing realistic relative scale

Evaluator

The image shows a woman standing next to a yellow school bus. The relative scale appears realistic: - The woman's height is appropriate relative to the bus door and the ground. - The bus wheels are large, roughly reaching her thigh/knee level, which is accurate for a heavy-duty vehicle. - The "SCHOOL BUS" lettering is positioned high above her head, consistent with the height of a school bus windshield. - The overall proportions of the bus (hood length, cabin height) relative to the human figur

A ladybug sitting on a large green leaf, shown at realistic fal/fal-ai/nano-banana-2PASS
A ladybug sitting on a large green leaf, shown at realistic proportions

Evaluator

The image shows a ladybug resting on a green leaf. The ladybug is small relative to the leaf, which occupies the majority of the frame. The scale of the ladybug compared to the leaf veins and surface texture appears natural and consistent with a macro photograph of a real insect on a plant. The proportions are realistic. VERDICT: PASS

A child holding a basketball, both at correct relative sizesfal/fal-ai/nano-banana-2PASS
A child holding a basketball, both at correct relative sizes

Evaluator

The image shows a young child holding a basketball labeled "JUNIOR". The size of the ball relative to the child's body and hands is physically consistent. A basketball is naturally large compared to a small child, and the "Junior" label indicates a smaller ball appropriate for youth, which matches the visual scale. The background hoop is also at a standard height relative to the child. VERDICT: PASS

Medium 100%vs100%
A tiny person standing on the rim of a coffee cup, looking dfal/fal-ai/nano-banana-2PASS
A tiny person standing on the rim of a coffee cup, looking down into it

Evaluator

The image clearly depicts a miniature figure (a "tiny person") standing on the rim of a standard-sized coffee cup. The scale is consistent with the prompt's request for a surreal size relationship where the person is small enough to stand on the cup's edge. The surrounding objects (spoon, book, table) provide context that confirms the cup is a normal size, making the person appropriately "tiny" by comparison. The lighting and perspective are consistent. VERDICT: PASS

A giant tabby cat walking between city skyscrapers like a kafal/fal-ai/nano-banana-2PASS
A giant tabby cat walking between city skyscrapers like a kaiju

Evaluator

The image depicts a massive tabby cat striding down a city street. The scale is consistent with the "kaiju" description: the cat is enormous relative to the cars, buses, and pedestrians (its paws are roughly the size of the vehicles), yet it fits within the canyon of skyscrapers, reaching perhaps 10-15 stories high while the buildings tower above it. The relative sizes are logical and consistent with the prompt. VERDICT: PASS

A miniature house sitting on the palm of someone's handfal/fal-ai/nano-banana-2PASS
A miniature house sitting on the palm of someone's hand

Evaluator

The image shows a detailed miniature cottage resting comfortably in the open palm of a person's hand. The scale is consistent with a collectible miniature model—it is small enough to be held easily but large enough to show intricate details like windows, a door, and roof tiles. The relative size between the hand and the house is realistic and matches the description of a "miniature house sitting on the palm." VERDICT: PASS

Hard 100%vs33%
A farm scene with a barn, tractor, farmer, cow, chicken, andfal/fal-ai/nano-banana-2PASS
A farm scene with a barn, tractor, farmer, cow, chicken, and a fence post, all at correct proportional scale

Evaluator

The image displays a farm scene with various elements. - **Barn:** Large, in the background, appropriate scale. - **Tractor:** Mid-ground, looks like a standard farm tractor. Its size relative to the farmer (who is walking nearby) seems plausible, perhaps slightly compact but within realistic bounds for a vintage model. - **Farmer:** Human scale, consistent with the tractor and barn. - **Cow:** Foreground left. It is large, consistent with a Holstein cow. Its size relative to the nearby fence p

A group photo of an elephant, a horse, a dog, a cat, and a mfal/fal-ai/nano-banana-2PASS
A group photo of an elephant, a horse, a dog, a cat, and a mouse, all standing in a line with correct real-world proportional sizes

Evaluator

The image displays an elephant, horse, dog, cat, and mouse arranged in a line from left to right. The relative sizes are consistent with real-world proportions: the elephant is the largest and tallest, followed by the horse, then the dog, then the cat, and finally the tiny mouse. The scaling between each animal is accurate (e.g., the horse is significantly larger than the dog, the cat is much larger than the mouse). VERDICT: PASS

A dinner table scene with a plate, fork, knife, wine glass, fal/fal-ai/nano-banana-2PASS
A dinner table scene with a plate, fork, knife, wine glass, salt shaker, and peppercorn, all at realistic relative sizes

Evaluator

The image displays a dinner table setting where the objects maintain realistic proportions relative to one another. The dinner plate is appropriately sized for the portion of food (salmon, asparagus, etc.). The fork and knife flanking the plate are standard dinnerware sizes. The wine glass is a typical size relative to the plate and table surface. The salt shaker and pepper grinder in the background are scaled correctly for table condiments. The perspective and depth of field further reinforce

Human realism 98%vs95%

Faces & Expressions100%vs92%
Easy 100%vs100%
A close-up portrait of a young woman with a warm natural smifal/fal-ai/nano-banana-2PASS
A close-up portrait of a young woman with a warm natural smile

Evaluator

The face in the image is largely symmetrical with natural, correctly proportioned features: the eyes, nose, and mouth are well-placed and balanced. The woman’s smile is wide and genuine, with visible teeth and crinkles around the eyes — a clear indicator of a warm, natural smile. There are no obvious distortions or unnatural artifacts; the lighting and composition enhance the authenticity of the expression. The prompt’s request for a “warm natural smile” is clearly met. VERDICT: PASS

A portrait of a middle-aged man with a calm, serious expressfal/fal-ai/nano-banana-2PASS
A portrait of a middle-aged man with a calm, serious expression

Evaluator

The face in the image is symmetric and features are anatomically correct — eyes, nose, mouth, and ears are proportionally aligned and natural. The man’s expression is calm and serious, conveyed through steady gaze, neutral mouth, and lack of smiling. There are no visible distortions or unnatural artifacts in the facial structure. The lighting and composition support a professional portrait style consistent with the prompt. VERDICT: PASS

A headshot of a teenager with a relaxed, neutral facefal/fal-ai/nano-banana-2PASS
A headshot of a teenager with a relaxed, neutral face

Evaluator

The face in the image is symmetric and features are anatomically correct: eyes, nose, mouth, and ears are proportionally aligned and natural. The teenager’s expression is neutral and relaxed, with no strong emotion conveyed — consistent with the prompt. There are no visible distortions; skin texture, hair, and facial structure appear realistic and well-rendered. The lighting and focus are appropriate for a headshot. VERDICT: PASS

Medium 100%vs100%
A close-up of a person's face showing clear disgust, nose wrfal/fal-ai/nano-banana-2PASS
A close-up of a person's face showing clear disgust, nose wrinkled and lip curled

Evaluator

The face in the image is largely symmetrical with correctly formed features — eyes, nose, mouth, and ears are proportionate and anatomically plausible. The expression clearly conveys disgust: the nose is visibly wrinkled, the lips are curled upward at the corners, the eyebrows are drawn together, and the forehead is furrowed — all classic indicators of disgust. There are no significant distortions; the facial muscles are rendered naturally, and the emotion is unmistakably readable. The lighting

A portrait capturing genuine surprise — raised eyebrows, widfal/fal-ai/nano-banana-2PASS
A portrait capturing genuine surprise — raised eyebrows, wide eyes, slightly open mouth

Evaluator

The face in the image is largely symmetric with correctly rendered features: the eyes, nose, and mouth are proportionally aligned, and the facial structure appears natural and undistorted. The emotion of surprise is clearly readable — the eyebrows are raised, the eyes are wide, and the mouth is slightly open, matching the prompt exactly. There are no noticeable distortions or unnatural artifacts. The expression is authentic and well-captured. VERDICT: PASS

A face showing quiet melancholy — downcast eyes, slightly drfal/fal-ai/nano-banana-2PASS
A face showing quiet melancholy — downcast eyes, slightly drawn mouth, distant gaze

Evaluator

The face is symmetric and features are anatomically correct — eyes, nose, mouth, and cheeks are proportionally aligned and natural. The expression conveys quiet melancholy: downcast eyes, slightly drawn mouth, and a distant, pensive gaze. There are no noticeable distortions or unnatural artifacts. The emotion is clearly readable and aligns with the prompt. VERDICT: PASS

Hard 100%vs100%
An elderly woman in her 80s with deep wrinkles and white haifal/fal-ai/nano-banana-2PASS
An elderly woman in her 80s with deep wrinkles and white hair, smiling warmly with kind eyes

Evaluator

The face in the image is largely symmetrical with natural, correct facial features. The elderly woman’s deep wrinkles are well-rendered around her eyes and mouth, consistent with someone in her 80s. Her white hair is voluminous and textured, and her expression conveys a warm, genuine smile with kind, crinkled eyes — clearly communicating the intended emotion. There are no obvious distortions; the proportions, lighting, and anatomy are realistic and coherent. The image successfully captures the r

A 5-year-old child with round cheeks and large eyes, crying fal/fal-ai/nano-banana-2PASS
A 5-year-old child with round cheeks and large eyes, crying with tears streaming down their face

Evaluator

The face in the image is largely symmetric with natural, correctly proportioned features. The child has round cheeks and large, expressive eyes, consistent with the prompt. Tears are clearly visible streaming down both cheeks, and the facial expression — furrowed brow, downturned mouth, and puffy eyes — strongly conveys crying. There are no significant distortions; the features are anatomically plausible and emotionally coherent. The child appears to be around 5 years old, and the overall compos

An elderly man in his 70s with age spots and thinning gray hfal/fal-ai/nano-banana-2PASS
An elderly man in his 70s with age spots and thinning gray hair, looking skeptically over reading glasses

Evaluator

The face is largely symmetric and features are anatomically correct: the eyes, nose, and mouth are proportionally aligned, and the facial structure is natural. Age spots are visible on the forehead and cheeks, and the hair is thinning gray, consistent with a man in his 70s. The reading glasses are worn correctly, and the expression — a skeptical, slightly narrowed gaze with a downturned mouth — clearly conveys doubt or skepticism. There are no noticeable distortions; the lighting, shadows, and t

Extreme 100%vs67%
A family photo with four people: a father beaming with pridefal/fal-ai/nano-banana-2PASS
A family photo with four people: a father beaming with pride, a mother smiling gently, a teenager looking bored, and a child grinning excitedly

Evaluator

All four faces in the image are symmetric with correct, natural features. The father’s face shows a clear, beaming expression of pride. The mother’s face displays a gentle, warm smile. The young boy’s face clearly conveys excitement through his wide grin and bright eyes. The teenager’s face clearly expresses boredom through her downturned mouth, lack of eye contact, and crossed arms. There are no distortions or unnatural features. The emotions are clearly readable and match the prompt. VERDICT:

A group of three friends at a table: one laughing with head fal/fal-ai/nano-banana-2PASS
A group of three friends at a table: one laughing with head tilted back, one looking shocked with wide eyes, and one rolling their eyes with a smirk

Evaluator

The image shows three individuals at a table, each displaying a distinct expression: - The woman on the left has wide eyes and an open mouth, with hands raised — clearly conveying shock or surprise. - The man in the center is laughing with his head tilted back and eyes closed — accurately portraying laughter. - The man on the right has a smirk and is looking sideways with a rolled-eye expression — clearly conveying disdain or sarcasm. All three faces are symmetrical and feature correctly rende

Three coworkers in a meeting: one looking frustrated with fufal/fal-ai/nano-banana-2PASS
Three coworkers in a meeting: one looking frustrated with furrowed brows, one nodding with a pleased expression, and one looking confused with a tilted head

Evaluator

The image shows three individuals seated at a conference table, each with a distinct facial expression that aligns with the prompt: - The man on the left has a furrowed brow and a stern, frustrated expression — consistent with the first requested emotion. - The woman in the center is smiling and nodding, conveying a pleased or satisfied expression — matching the second requested emotion. - The man on the right has a tilted head and a quizzical, confused look — matching the third requested emoti

Full Body100%vs100%
Easy 100%vs100%
A woman standing upright in a relaxed pose, arms at her sidefal/fal-ai/nano-banana-2PASS
A woman standing upright in a relaxed pose, arms at her sides, wearing jeans and a white t-shirt

Evaluator

The woman in the image is standing upright in a relaxed pose with her arms at her sides, wearing jeans and a white t-shirt — fully matching the prompt. - Limb count: Correct — two arms, two legs, both visible and intact. - Proportions: Anatomically correct — head, torso, limbs are proportionally balanced; no obvious distortions. - Pose: Recognizable — upright, relaxed stance with arms at sides, natural posture. - No distortions: The figure appears natural and undistorted; no extra limbs, fused

A man standing straight facing the camera, hands in pockets,fal/fal-ai/nano-banana-2PASS
A man standing straight facing the camera, hands in pockets, normal proportions

Evaluator

The man in the image is standing straight, facing the camera, with both hands in his pockets — exactly matching the prompt. His proportions appear normal: head, torso, arms, and legs are in proportion to each other with no obvious deformities. Limb count is correct — two arms, two legs, and all joints appear anatomically placed. The pose is recognizable and natural for someone standing casually with hands in pockets. There are no visible distortions in the limbs or body structure. The clothing a

A person standing in a neutral pose in a park, full body visfal/fal-ai/nano-banana-2PASS
A person standing in a neutral pose in a park, full body visible from head to feet

Evaluator

The image shows a full-body shot of a person standing in a park, as requested. The person is positioned centrally, facing the camera, with arms hanging naturally at their sides and feet shoulder-width apart — a neutral, recognizable standing pose. Anatomical correctness: - Limb count: Two arms, two legs — correct. - Proportions: Head, torso, arms, and legs appear proportionate and realistic. No obvious distortions in limb length or joint placement. - Pose: The pose is anatomically plausible — s

Medium 100%vs100%
A woman mid-stride running through a park, hair and clothes fal/fal-ai/nano-banana-2PASS
A woman mid-stride running through a park, hair and clothes showing motion

Evaluator

The woman in the image is captured mid-stride while running, with her hair and clothing showing clear motion — consistent with the prompt. Her limbs are correctly proportioned and anatomically accurate: both arms are bent and swinging naturally, legs are positioned in a typical running gait with one foot off the ground and the other pushing off. The pose is recognizable as a dynamic running motion, with the body leaning slightly forward and core engaged. There are no visible distortions in limb

A man captured mid-jump over a puddle, body in the air with fal/fal-ai/nano-banana-2PASS
A man captured mid-jump over a puddle, body in the air with bent knees

Evaluator

The image shows a man mid-air, leaping over a muddy puddle in a forest setting. His body is captured in a dynamic, athletic pose with bent knees and arms slightly forward, consistent with a jump or hop. The limbs are all present — two arms, two legs, and the torso — and their proportions appear anatomically accurate. The pose is recognizable as a jump over an obstacle, and the motion is supported by visible splashes of mud and water beneath his feet, indicating the action is physically plausible

A dancer in a dynamic spin, dress flowing outward with one lfal/fal-ai/nano-banana-2PASS
A dancer in a dynamic spin, dress flowing outward with one leg extended

Evaluator

The dancer is captured mid-spin, with her dress flowing outward as described, and one leg extended in a classic ballet pose (a développé or attitude position). She is en pointe on one foot, which is anatomically plausible for a trained dancer. Limb count is correct: two arms, two legs, and the torso are all intact and proportionate. The pose is recognizable as a dynamic, expressive dance movement, consistent with classical ballet or contemporary dance. There are no obvious anatomical distortions

Hard 100%vs100%
A person in a yoga tree pose — standing on one leg with the fal/fal-ai/nano-banana-2PASS
A person in a yoga tree pose — standing on one leg with the other foot pressed to the inner thigh, arms raised overhead

Evaluator

The image shows a person performing a yoga pose. The pose matches the description: standing on one leg with the other foot pressed to the inner thigh, arms raised overhead with hands clasped. The limb count is correct — two arms, two legs, two feet — and proportions appear anatomically plausible. The pose is clearly recognizable as Vrksasana (Tree Pose). There are no obvious distortions in the limbs or body structure; the alignment of the torso, hips, and legs is consistent with a standard yoga

A cellist seated with correct posture, legs around the instrfal/fal-ai/nano-banana-2PASS
A cellist seated with correct posture, legs around the instrument, bow arm extended

Evaluator

The cellist in the image is seated with correct posture, and the instrument is properly positioned between her legs, resting on a stand. Her bow arm is extended and actively engaged in playing the cello, with the bow drawn across the strings — consistent with the described action. Her left hand is positioned on the fingerboard, and her right hand holds the bow correctly. Limb count is normal (two arms, two legs), and proportions appear anatomically accurate. There are no obvious distortions in t

A rock climber clinging to a cliff face with arms and legs efal/fal-ai/nano-banana-2PASS
A rock climber clinging to a cliff face with arms and legs extended to different holds

Evaluator

The image shows a full-body shot of a male rock climber on a steep cliff face. He is wearing climbing gear, including a harness, rope, and climbing shoes. His arms are extended to grip holds on the rock, and his legs are spread apart — one foot on a ledge, the other reaching for a hold — which is a recognizable and physically plausible climbing stance. Anatomical inspection: - Limb count: Two arms, two legs — correct. - Proportions: The figure’s proportions appear natural and consistent with hu

Extreme 100%vs100%
Two tango dancers in a close embrace, the man dipping the wofal/fal-ai/nano-banana-2PASS
Two tango dancers in a close embrace, the man dipping the woman backward with intertwined legs

Evaluator

The image depicts a tango dance pose with the man dipping the woman backward. The woman’s legs are intertwined with the man’s legs — her right leg is wrapped around his right thigh, and her left leg is extended back, creating a classic tango “dip” with leg entanglement. The man’s posture supports her weight, and their bodies are in close embrace as described. Limb count is correct: both dancers have two arms, two legs, and the correct number of fingers and toes are visible. Proportions are anat

Two gymnasts performing a synchronized handstand, side by sifal/fal-ai/nano-banana-2PASS
Two gymnasts performing a synchronized handstand, side by side with identical body alignment

Evaluator

The image shows two female gymnasts performing a synchronized handstand on a blue competition floor, side by side. Their bodies are nearly identical in alignment — both are inverted, legs straight and together, heads down, hands planted shoulder-width apart, and wrists supported by wrist guards. Their limbs are fully intact: two arms, two legs per person, with no missing or extra limbs. Proportions appear anatomically accurate — limbs are proportionate to torso, and the handstand pose is physica

Two soccer players mid-tackle, one sliding and the other jumfal/fal-ai/nano-banana-2PASS
Two soccer players mid-tackle, one sliding and the other jumping over with the ball at their feet

Evaluator

The image shows two soccer players in a dynamic, realistic action shot. The player in the blue and white kit is sliding on the grass, with his body low to the ground, one hand touching the turf, and his legs extended — a typical sliding tackle. The player in the red and black kit is airborne, jumping over the sliding player, with the ball at his feet, suggesting he’s maintaining control while evading the tackle. Anatomically, both players have correct limb counts (two arms, two legs each), and

Hands92%vs92%
Easy 100%vs100%
A woman holding her hands out in front of her palms-up, all fal/fal-ai/nano-banana-2PASS
A woman holding her hands out in front of her palms-up, all ten fingers clearly visible

Evaluator

Both hands are clearly visible, palms up, and all ten fingers are distinctly visible — five on each hand. The fingers are anatomically correct in length, spacing, and curvature, with no missing, fused, or malformed digits. The gesture is natural and consistent with the prompt: hands held out in front, palms up, fingers spread. No anomalies are present. VERDICT: PASS

A person standing with both hands visible at their sides, fifal/fal-ai/nano-banana-2PASS
A person standing with both hands visible at their sides, fingers relaxed and naturally spread

Evaluator

Both hands are visible at the person’s sides, fingers relaxed and naturally spread, as requested. Counting the fingers on each hand: - Left hand: Thumb, index, middle, ring, pinky — 5 fingers. - Right hand: Thumb, index, middle, ring, pinky — 5 fingers. The grip/gesture is anatomically correct. The fingers are relaxed, slightly curved, and naturally spread — consistent with a neutral, resting hand position. No anomalies are present (e.g., missing fingers, extra digits, malformed joints, or unn

A man with arms crossed, both hands resting on opposite uppefal/fal-ai/nano-banana-2PASS
A man with arms crossed, both hands resting on opposite upper arms with fingers visible

Evaluator

Both hands are visible in the image, resting on opposite upper arms as described in the prompt. Left hand (on right arm): 5 fingers clearly visible — thumb, index, middle, ring, pinky. Right hand (on left arm): 5 fingers clearly visible — thumb, index, middle, ring, pinky. The grip is anatomically plausible: the hands are crossed, with fingers resting on the upper arms, and the posture is natural for a relaxed crossed-arm stance. No fingers are missing or duplicated. The fingers are proportion

Medium 100%vs100%
A person holding a white ceramic coffee mug by the handle wifal/fal-ai/nano-banana-2PASS
A person holding a white ceramic coffee mug by the handle with their right hand

Evaluator

The visible right hand holding the mug shows all five fingers: thumb, index, middle, ring, and pinky — arranged naturally around the handle. The grip is anatomically correct: the thumb is on the side of the handle, and the other fingers wrap around from the other side, forming a secure, natural hold. The left hand is partially visible, resting on the table, and also appears to have five fingers, though less clearly defined due to angle and focus. No anomalies are present — the fingers are propo

A person playing an acoustic guitar with left hand on the frfal/fal-ai/nano-banana-2PASS
A person playing an acoustic guitar with left hand on the fretboard and right hand strumming

Evaluator

Left hand (on fretboard): 5 fingers visible — thumb, index, middle, ring, pinky — all positioned correctly for fretting strings. Anatomically accurate grip, with fingers curved over the frets. Right hand (strumming): 5 fingers visible — thumb, index, middle, ring, pinky — all present and positioned naturally for strumming. Thumb is near the soundhole, other fingers are extended toward the strings, consistent with strumming posture. No anomalies detected. All fingers are present and anatomicall

A woman writing in a notebook with a pen gripped correctly ifal/fal-ai/nano-banana-2PASS
A woman writing in a notebook with a pen gripped correctly in her right hand

Evaluator

The right hand (writing hand) clearly shows five fingers: thumb, index, middle, ring, and pinky — all visible and anatomically positioned around the pen in a standard tripod grip. The left hand is resting on the notebook, also showing five fingers clearly — thumb, index, middle, ring, and pinky — with natural positioning for support. The grip on the pen is anatomically correct: the pen is held between the thumb and index finger, with the middle finger providing support, which is a standard and

Hard 67%vs67%
A hand giving a thumbs-up with four fingers curled and thumbfal/fal-ai/nano-banana-2PASS
A hand giving a thumbs-up with four fingers curled and thumb extended upward

Evaluator

The image shows a single hand giving a thumbs-up gesture. The thumb is extended upward, and the other four fingers (index, middle, ring, and pinky) are curled into a fist. All five fingers are clearly visible and anatomically correct — no fingers are missing, duplicated, or distorted. The gesture matches the prompt: “A hand giving a thumbs-up with four fingers curled and thumb extended upward.” The hand appears natural, with realistic skin texture, knuckle definition, and finger alignment. No

A person making a peace sign with their right hand, clearly fal/fal-ai/nano-banana-2PASS
A person making a peace sign with their right hand, clearly showing two fingers up and three curled

Evaluator

The image shows a person making a peace sign with their right hand. The gesture clearly displays the index and middle fingers extended upward, while the ring finger, pinky, and thumb are curled or positioned downward — consistent with the “peace sign” gesture. Counting the visible fingers on the right hand: - Index finger: visible - Middle finger: visible - Ring finger: curled, visible - Pinky: curled, visible - Thumb: curled, visible That’s five fingers — all present and clearly distinguishab

A person counting to three on their fingers, with index, midfal/fal-ai/nano-banana-2FAIL
A person counting to three on their fingers, with index, middle, and ring fingers extended

Evaluator

The visible hand in the image (the one raised and counting) clearly shows exactly three fingers extended: the index, middle, and ring fingers — matching the prompt. The thumb is curled inward, and the pinky is not extended, which is anatomically correct for this gesture. The other hand resting on the table is partially visible and shows five fingers (thumb, index, middle, ring, pinky) — but since the prompt only asked to count the fingers on the hand that is “counting to three,” we focus on that

Extreme 100%vs100%
Two people doing a high-five, palms meeting with all fingersfal/fal-ai/nano-banana-2PASS
Two people doing a high-five, palms meeting with all fingers extended on both hands

Evaluator

Both hands in the high-five gesture are clearly visible, and each hand shows all five fingers extended — thumb, index, middle, ring, and pinky — with no fingers missing or fused. The palms are meeting squarely, and the fingers are spread naturally, consistent with a high-five gesture. The anatomy is accurate: no extra fingers, no missing digits, no deformities, and the hand proportions and finger alignment are realistic. The gesture matches the prompt exactly. VERDICT: PASS

Two people shaking hands in a professional setting, all fingfal/fal-ai/nano-banana-2PASS
Two people shaking hands in a professional setting, all fingers of both hands anatomically correct

Evaluator

Counting the fingers on each visible hand in the handshake: - The woman’s right hand (visible on the left side of the image) clearly shows five fingers: thumb, index, middle, ring, and pinky. All are anatomically present and properly aligned. - The man’s left hand (visible on the right side of the image) also clearly shows five fingers. The grip is a standard professional handshake — fingers interlaced, palms slightly angled, thumbs not touching — which is anatomically correct and culturally ap

One person handing a small gift box to another person, both fal/fal-ai/nano-banana-2PASS
One person handing a small gift box to another person, both sets of hands gripping the box correctly

Evaluator

Both hands are clearly visible — the woman’s left hand and the man’s right hand — and each has five fingers: thumb, index, middle, ring, and pinky. All fingers are anatomically positioned and appear natural in their grip around the gift box. The hands are gripping the box in a way that is consistent with real-world interaction — fingers wrapping around the sides, thumbs supporting from the front or side — and there are no anomalies such as extra fingers, missing fingers, or unnatural joint posit

Multi-Subject100%vs100%
Easy 100%vs100%
Two men at a cafe: one with a beard and glasses wearing a grfal/fal-ai/nano-banana-2PASS
Two men at a cafe: one with a beard and glasses wearing a green sweater, the other clean-shaven in a black hoodie

Evaluator

Person 1 (left, foreground): - Beard: Present, full and well-defined. - Glasses: Wearing black-rimmed glasses. - Sweater: Wearing a dark green, ribbed knit sweater. - Matches description: ✅ Yes. Person 2 (right, foreground): - Beard: Clean-shaven. - Hoodie: Wearing a black hoodie with a small white mountain logo on the chest. - Matches description: ✅ Yes. Both individuals are visually distinct and clearly match the described features. VERDICT: PASS

Two women standing side by side: one with short blonde hair fal/fal-ai/nano-banana-2PASS
Two women standing side by side: one with short blonde hair wearing a red jacket, the other with long black hair wearing a blue dress

Evaluator

Person 1 (left): - Hair: Short, blonde, styled neatly. - Clothing: Wearing a red zip-up jacket over a striped shirt, paired with dark jeans and white sneakers. - Features: Smiling, standing upright, facing forward. Person 2 (right): - Hair: Long, black, wavy, falling over shoulders. - Clothing: Wearing a blue dress with three-quarter sleeves and a flared skirt, carrying a brown crossbody bag. - Features: Smiling, standing upright, facing forward. Both individuals are visually distinct and matc

Two friends posing: one tall with curly red hair in denim ovfal/fal-ai/nano-banana-2PASS
Two friends posing: one tall with curly red hair in denim overalls, the other short with straight brown hair in a yellow sundress

Evaluator

Person 1 (tall): - Hair: Curly, red (appears reddish-orange, consistent with "curly red hair") - Clothing: Denim overalls (worn over a striped shirt), ripped at knees - Height: Clearly taller than the other person - Pose: Arms around the other person, smiling Person 2 (short): - Hair: Straight, brown (with bangs), matches "straight brown hair" - Clothing: Yellow sundress with floral pattern - Height: Clearly shorter than the other person - Pose: Smiling, leaning into the taller person Both i

Medium 100%vs100%
Four people at a dinner table: a bald man in a suit, a womanfal/fal-ai/nano-banana-2PASS
Four people at a dinner table: a bald man in a suit, a woman with silver hair in a red blouse, a young man with dreadlocks in a denim jacket, and a woman with a hijab in a green dress

Evaluator

- Bald man in a suit: Present. He is on the far left, bald with a beard, wearing a dark suit and white shirt. Matches description. - Woman with silver hair in a red blouse: Present. Seated next to the bald man, with short silver hair and wearing a red blouse. Matches description. - Young man with dreadlocks in a denim jacket: Present. Seated across from the woman in the hijab, has dark dreadlocks and wears a denim jacket over a black shirt. Matches description. - Woman with a hijab in a green dr

Three musicians on stage: a tall woman with short pink hair fal/fal-ai/nano-banana-2PASS
Three musicians on stage: a tall woman with short pink hair playing bass, a man with a beard and bandana on drums, and a slim man with glasses playing keyboard

Evaluator

- Tall woman with short pink hair playing bass: Present. She has short, spiky pink hair, is playing a bass guitar, and is wearing ripped jeans and a graphic tee. Matches description. - Man with beard and bandana on drums: Present. He has a full beard, is wearing a black bandana, and is seated behind a drum kit. Matches description. - Slim man with glasses playing keyboard: Present. He is standing, wearing glasses, and playing a Korg Kronos keyboard. Matches description. All three individuals

Three hikers on a trail: a man with a backpack and sunhat, afal/fal-ai/nano-banana-2PASS
Three hikers on a trail: a man with a backpack and sunhat, a woman with braided hair and hiking poles, and a teenager with a baseball cap and water bottle

Evaluator

Person 1 (Man): - Observed traits: Wearing a tan sunhat, a blue short-sleeved shirt, khaki shorts, hiking boots, and a large green backpack. He is smiling and walking on the trail. - Matches description: Yes — backpack and sunhat are clearly present. Person 2 (Woman): - Observed traits: Wearing a teal shirt and shorts, has long braided hair, holding two hiking poles, and wearing a backpack. She is smiling and walking beside the man. - Matches description: Yes — braided hair and hiking poles a

Truthfulness 93%vs11%

Photorealism100%vs0%
Medium 100%vs0%
A still life on a wooden table featuring a clear glass of wafal/fal-ai/nano-banana-2PASS
A still life on a wooden table featuring a clear glass of water, a polished silver spoon, a folded linen napkin, and a ripe red apple — each material rendered with accurate texture and light behavior

Evaluator

The image accurately renders the requested materials. The glass shows proper refraction and transparency, the spoon exhibits sharp metallic reflections, the wood has a convincing grain and matte finish, and the linen napkin displays appropriate fabric texture. The apple’s skin reflects light realistically. All materials behave correctly under the lighting conditions. VERDICT: PASS

A workspace desk with a brushed aluminum laptop, a leather-bfal/fal-ai/nano-banana-2PASS
A workspace desk with a brushed aluminum laptop, a leather-bound notebook, a ceramic coffee mug, and a glass paperweight — all materials visually distinct and realistic

Evaluator

The image accurately renders the requested materials with high fidelity. The laptop exhibits a realistic brushed aluminum finish with appropriate reflections. The notebook shows a convincing leather texture with wear and grain. The ceramic mug displays a matte, speckled glaze, while the glass paperweight demonstrates correct refraction and transparency. The wooden desk has a natural grain and texture. All materials are visually distinct and realistic. VERDICT: PASS

A kitchen counter with a stainless steel pot, a wooden cuttifal/fal-ai/nano-banana-2PASS
A kitchen counter with a stainless steel pot, a wooden cutting board, a glass bottle of olive oil, and a cotton dish towel — each surface reflecting light correctly

Evaluator

The image accurately renders the requested materials. The stainless steel pot shows sharp, distorted reflections of the surroundings. The glass bottle exhibits correct translucency and refraction, with the liquid visible inside. The wooden cutting board displays a natural grain texture and matte finish, while the cotton towel shows appropriate fabric folds and softness. All surfaces interact with light realistically. VERDICT: PASS

Physics & Reflections92%vs8%
Easy 100%vs33%
A red sphere on a white surface with a single shadow cast tofal/fal-ai/nano-banana-2PASS
A red sphere on a white surface with a single shadow cast to the right, consistent with a light source from the upper left

Evaluator

The red sphere casts a shadow to the right, consistent with a light source from the upper left. The shadow’s shape and softness are physically plausible for a diffuse light source. The sphere’s highlight is on the upper left, matching the lighting direction. No distortions or color anomalies are present. VERDICT: PASS

A coffee mug on a sunny windowsill casting a sharp shadow tofal/fal-ai/nano-banana-2PASS
A coffee mug on a sunny windowsill casting a sharp shadow to the left

Evaluator

The sunlight enters from the right side of the frame, casting shadows to the left. The coffee mug casts a distinct, sharp shadow to its left on the windowsill, consistent with the light source. The books and plant also cast shadows in the same direction. The reflections in the window glass are minimal but plausible for a sunny day. The shadow's shape matches the mug's form. VERDICT: PASS

A person standing outdoors at midday with a short shadow dirfal/fal-ai/nano-banana-2PASS
A person standing outdoors at midday with a short shadow directly below them

Evaluator

The shadow is cast directly beneath the subject, consistent with midday sun positioning. The direction and length are physically plausible for a high sun angle. The shadow’s shape matches the person’s silhouette without distortion. Color is appropriately dark and blends naturally with the stone pavement. No reflections are expected in this outdoor scene, and none are present. Overall, the shadow behavior aligns with real-world physics. VERDICT: PASS

Medium 67%vs0%
A woman standing in front of a full-length mirror, her reflefal/fal-ai/nano-banana-2FAIL
A woman standing in front of a full-length mirror, her reflection accurately showing the back of her outfit and reversed orientation

Evaluator

The reflection is physically implausible. The woman is facing the mirror, so her reflection should show her front. Instead, the reflection shows her front while the real woman’s back is visible — this is correct for orientation, but the reflection’s pose and hand placement do not match the real body’s posture (e.g., one arm raised in reflection, none in reality). Also, the reflection’s facial expression and head tilt don’t align with a true mirror image. Shadows and lighting are consistent, but

A vase of flowers on a glass table with a clear reflection vfal/fal-ai/nano-banana-2PASS
A vase of flowers on a glass table with a clear reflection visible on the table surface

Evaluator

The reflection on the glass table is physically plausible. It correctly mirrors the vase and flowers with appropriate orientation, slight distortion due to the glass surface, and accurate color representation. The reflection aligns with the light source and object placement, maintaining realism in direction and clarity. VERDICT: PASS

A cat sitting on a polished marble floor with its reflectionfal/fal-ai/nano-banana-2PASS
A cat sitting on a polished marble floor with its reflection visible below

Evaluator

The reflection is physically plausible. It appears directly beneath the cat, matching its orientation and posture. The slight blur and distortion are consistent with a polished but not perfectly mirror-like marble surface. The reflection’s color and brightness align with the cat’s appearance, and the lighting direction (from the left) is consistent with the shadows and highlights on the floor. No obvious artifacts or inconsistencies are present. VERDICT: PASS

Hard 100%vs0%
A row of trees reflected in a calm lake at sunset, with the fal/fal-ai/nano-banana-2PASS
A row of trees reflected in a calm lake at sunset, with the reflection slightly darker and gently rippled

Evaluator

The reflections are physically plausible. The trees are mirrored vertically in the water with appropriate distortion from gentle ripples. The reflection is slightly darker than the actual trees, consistent with light absorption by water. Colors match the sunset sky and tree silhouettes. Direction and orientation are correct — no inversion or misalignment. VERDICT: PASS

A city skyline reflected in a rain puddle on a street, with fal/fal-ai/nano-banana-2PASS
A city skyline reflected in a rain puddle on a street, with mild distortion and color shift

Evaluator

The reflection in the puddle is physically plausible. It correctly mirrors the skyline’s orientation, with appropriate distortion from ripples and a natural color shift due to water refraction and ambient lighting. The wet street surface enhances realism, and the reflection aligns with the light sources and building positions above. VERDICT: PASS

A mountain range reflected in a still alpine lake, with the fal/fal-ai/nano-banana-2PASS
A mountain range reflected in a still alpine lake, with the reflection inverted and subtly muted in color

Evaluator

The reflection is physically plausible. It is correctly inverted, matching the mountain range’s orientation. The colors are subtly muted, consistent with real-world water reflections. Minor ripples cause slight distortion, which is natural. Shadows and lighting align with the scene’s direction. No anomalies detected. VERDICT: PASS

Extreme 100%vs0%
A clear glass sphere sitting on a mirror surface near a poolfal/fal-ai/nano-banana-2PASS
A clear glass sphere sitting on a mirror surface near a pool of water, showing refraction through the sphere, reflection on the mirror, and water reflection simultaneously

Evaluator

The reflections and refractions are physically plausible. The crystal ball correctly inverts the scene (sky at the bottom, ground at the top) due to refraction. The mirror reflects the sphere accurately, maintaining orientation. The wet stone surface shows a distorted reflection of the sphere consistent with its texture. Lighting directions are consistent across all elements. VERDICT: PASS

A chrome sculpture in a room with a glass floor and large wifal/fal-ai/nano-banana-2PASS
A chrome sculpture in a room with a glass floor and large windows, showing multiple reflections and environmental mapping on every surface

Evaluator

The reflections are physically plausible. The chrome sculpture accurately mirrors the surrounding windows, cityscape, and ceiling lights with appropriate distortion based on its curved geometry. The glass floor reflects the sculpture and figures above while allowing visibility of the lower level, consistent with a transparent reflective surface. Shadows and highlights align with the ambient lighting from the windows and interior fixtures. VERDICT: PASS

A crystal wine glass on a polished marble counter next to a fal/fal-ai/nano-banana-2PASS
A crystal wine glass on a polished marble counter next to a window overlooking a lake — showing refraction in the glass, reflection on the marble, and the lake's own reflective surface

Evaluator

The reflections and refractions are physically plausible. The wine glass shows realistic distortion of the background through its curved surface, with proper refraction of light. The marble countertop reflects the glass stem and base accurately, including subtle color shifts from the red wine. The lake’s surface mirrors the sky and mountains with appropriate softness and ripple distortion. All elements align in direction and orientation. VERDICT: PASS

World Knowledge92%vs17%
Easy 100%vs33%
The Eiffel Tower in Paris on a clear day, architecturally acfal/fal-ai/nano-banana-2PASS
The Eiffel Tower in Paris on a clear day, architecturally accurate with its iron lattice structure and three levels

Evaluator

The image depicts the Eiffel Tower with high architectural accuracy. The iron lattice structure, the four arched legs, and the three distinct levels (including the top spire) are correctly rendered. The surrounding Parisian skyline and the Seine River are also recognizable and appropriately placed. The lighting and weather conditions match the prompt’s request for a clear day. VERDICT: PASS

The Taj Mahal in Agra seen from the reflecting pool, with acfal/fal-ai/nano-banana-2PASS
The Taj Mahal in Agra seen from the reflecting pool, with accurate dome, minarets, and symmetry

Evaluator

The image depicts the Taj Mahal with high architectural accuracy. The central dome, four minarets, and the reflecting pool are correctly positioned and proportioned. The symmetry is precise, and the reflection in the water is realistic. The surrounding gardens and pathways also match the real-world layout. No significant inaccuracies are present. VERDICT: PASS

The Statue of Liberty on her island pedestal, with correct tfal/fal-ai/nano-banana-2PASS
The Statue of Liberty on her island pedestal, with correct torch, crown, tablet, and green patina

Evaluator

The Statue of Liberty is recognizable and accurately depicted with the correct torch, crown, tablet, and green patina. The pedestal and surrounding island are also consistent with reality. The background skyline of New York City is plausible and enhances the scene’s authenticity. No significant inaccuracies are present. VERDICT: PASS

Medium 100%vs33%
A traditional Japanese shamisen instrument with accurate thrfal/fal-ai/nano-banana-2PASS
A traditional Japanese shamisen instrument with accurate three-stringed design, wooden body, and bachi plectrum

Evaluator

The image depicts a shamisen with high fidelity. The instrument features the characteristic square wooden body (tsuzumi), taut skin head, long neck, and three strings. The bachi (plectrum) is correctly placed nearby. The setting is a traditional Japanese room with tatami mats and shoji screens, enhancing realism. No factual or architectural inaccuracies are present. VERDICT: PASS

A Japanese kintsugi bowl — cracked ceramic repaired with visfal/fal-ai/nano-banana-2PASS
A Japanese kintsugi bowl — cracked ceramic repaired with visible gold lacquer lines

Evaluator

The image accurately depicts a Japanese kintsugi bowl with visible gold lacquer lines repairing cracks in the ceramic. The setting, including the wooden table and traditional Japanese elements like the shoji screen and tea whisk, enhances the authenticity. The bowl’s texture and the gold lines are realistic and well-rendered. VERDICT: PASS

A medieval astrolabe with accurate rete, tympan, and engravefal/fal-ai/nano-banana-2PASS
A medieval astrolabe with accurate rete, tympan, and engraved degree markings on brass

Evaluator

The subject is clearly recognizable as an astrolabe. The brass material, engraved degree markings, rete, and tympan are all present and stylistically appropriate for a medieval or early modern instrument. While some text labels (e.g., “LONDINI,” “SIRIUS”) are plausible, others like “LINEA MERIDIANA” appear anachronistic or non-standard for authentic medieval astrolabes. However, the core components are accurately represented in form and function. VERDICT: PASS

Hard 100%vs0%
A detailed diagram of the water cycle showing evaporation frfal/fal-ai/nano-banana-2PASS
A detailed diagram of the water cycle showing evaporation from the ocean, condensation forming clouds, precipitation as rain, and collection in rivers flowing back to the sea

Evaluator

The image is a clear, educational diagram of the water cycle. It accurately depicts evaporation from the ocean, condensation forming clouds, precipitation (rain and snow), surface runoff, infiltration into groundwater, and collection in rivers flowing back to the sea. All labeled components are scientifically correct and visually represented in a standard, recognizable manner. VERDICT: PASS

A cross-section showing tectonic plates at a convergent bounfal/fal-ai/nano-banana-2PASS
A cross-section showing tectonic plates at a convergent boundary with subduction, a trench, volcanic arc, and layered mantle

Evaluator

The image is a scientifically accurate and clearly labeled diagram of a convergent plate boundary involving subduction. It correctly depicts the oceanic trench, accretionary prism, forearc basin, volcanic arc, magma chamber, mantle wedge, and layered mantle structure (asthenosphere, mesosphere). The processes shown — such as dehydration of the subducting slab triggering melting and rising magma — are factually correct. Minor labeling inconsistencies (e.g., “OCEANIC LITHE” instead of “LITHOSPHERE

An anatomical illustration of the human heart showing four cfal/fal-ai/nano-banana-2PASS
An anatomical illustration of the human heart showing four chambers, valves, aorta, pulmonary arteries, and veins with correct placement

Evaluator

The image is a clear, recognizable anatomical illustration of the human heart. It correctly depicts the four chambers (right atrium, right ventricle, left atrium, left ventricle), major valves (tricuspid, mitral, aortic), and major vessels (aorta, pulmonary arteries, pulmonary veins, superior/inferior vena cava). The placement and labeling are factually accurate for a standard medical diagram. Arrows indicate correct blood flow direction. No significant inaccuracies detected. VERDICT: PASS

Extreme 67%vs0%
A Morpho menelaus butterfly with accurate iridescent blue dofal/fal-ai/nano-banana-2FAIL
A Morpho menelaus butterfly with accurate iridescent blue dorsal wings, brown ventral wing pattern with eyespots, and correct body morphology

Evaluator

The image depicts a butterfly with mismatched wings: the left side shows the bright blue dorsal pattern of a Morpho, while the right side displays the brown, eyespotted ventral pattern. In reality, a single butterfly cannot display both dorsal and ventral patterns simultaneously on opposite sides of its body in this manner. This is a biological impossibility and a clear factual inaccuracy. VERDICT: FAIL

The Hagia Sophia interior showing the massive central dome, fal/fal-ai/nano-banana-2PASS
The Hagia Sophia interior showing the massive central dome, pendentives, semi-domes, and Islamic calligraphy medallions alongside Byzantine mosaics

Evaluator

The image accurately depicts the interior of the Hagia Sophia, showcasing its iconic central dome, semi-domes, and pendentives. The Islamic calligraphy medallions are correctly placed, and the Byzantine mosaics are visible. The architectural details, such as the columns, arches, and chandeliers, are consistent with the actual structure. The lighting and perspective enhance the grandeur of the space, making it recognizable and factually accurate. VERDICT: PASS

A specimen of bismuth crystal showing accurate iridescent oxfal/fal-ai/nano-banana-2PASS
A specimen of bismuth crystal showing accurate iridescent oxide layers, geometric hopper crystal formation, and characteristic staircase structure

Evaluator

The image depicts a bismuth crystal with the characteristic geometric hopper formation and iridescent oxide layers. The staircase structure is accurately represented, and the colors are vibrant and realistic. The label on the display stand also correctly identifies it as a bismuth crystal from Germany. Overall, the depiction is factually accurate and recognizable. VERDICT: PASS

Professional Studio 89%vs85%

Camera & Lighting100%vs100%
Easy 100%vs100%
An aerial bird's-eye view looking straight down at a trafficfal/fal-ai/nano-banana-2PASS
An aerial bird's-eye view looking straight down at a traffic roundabout with cars and trees

Evaluator

The image matches the prompt's requirements: 1. **Perspective:** The image is a true aerial bird's-eye view looking straight down at a traffic roundabout. The verticality and top-down angle are consistent with the prompt. 2. **Depth of Field:** The entire scene is in sharp focus from the center of the roundabout to the edges of the buildings and streets, which is typical for high-altitude aerial photography. 3. **Lighting Pattern:** The lighting is consistent with a bright, sunny day. There

A close-up macro shot of a single dewdrop on a rose petal, sfal/fal-ai/nano-banana-2PASS
A close-up macro shot of a single dewdrop on a rose petal, shallow depth of field

Evaluator

The image matches the prompt's specifications: 1. **Perspective/Shot Type**: The image is a close-up macro shot focusing on a single, prominent dewdrop resting on a red rose petal. 2. **Depth of Field**: The image features a shallow depth of field, where the dewdrop and the immediate petal are in sharp focus, while the background and the rest of the rose are softly blurred (bokeh effect). 3. **Lighting**: The lighting is soft and natural, highlighting the texture of the petal and the clarity

A wide-angle shot of a modern living room interior showing efal/fal-ai/nano-banana-2PASS
A wide-angle shot of a modern living room interior showing expansive space with slight barrel distortion at the edges

Evaluator

The image shows a modern living room with a curved architectural structure. 1. **Wide-angle shot/Expansive space**: The image uses a fisheye/circular lens effect that creates a very wide field of view, capturing a large expanse of the room and the view outside. 2. **Barrel Distortion**: The prompt specifically requested "slight barrel distortion at the edges." The image exhibits extreme barrel distortion (a fisheye effect) where the edges are heavily curved and circular, rather than just a "sl

Medium 100%vs100%
A high-key portrait of a person against a bright white backgfal/fal-ai/nano-banana-2PASS
A high-key portrait of a person against a bright white background, minimal shadows, airy and luminous

Evaluator

The image depicts a person against a bright white background with very soft, minimal shadows, which aligns perfectly with the "high-key" description. The lighting is bright, airy, and luminous, creating a clean and high-key aesthetic. The depth of field is shallow, keeping the subject in focus while the background remains a seamless, bright white, which is typical for this style of portraiture. VERDICT: PASS

A portrait lit with classic Rembrandt lighting — triangle offal/fal-ai/nano-banana-2PASS
A portrait lit with classic Rembrandt lighting — triangle of light on the shadowed cheek, moody atmosphere

Evaluator

The image matches the specified criteria: 1. **Lighting Pattern:** The subject exhibits classic Rembrandt lighting. There is a distinct, small triangle of light visible on the shadowed cheek (the side of the face away from the primary light source), which is the defining characteristic of this lighting style. 2. **Atmosphere:** The overall atmosphere is moody and dark, with deep shadows and a low-key lighting setup that complements the "moody atmosphere" requirement. 3. **Perspective and Dep

A landscape photograph bathed in golden hour light — long wafal/fal-ai/nano-banana-2PASS
A landscape photograph bathed in golden hour light — long warm shadows, orange sky, soft glow

Evaluator

The image perfectly matches the specified camera and lighting descriptions: 1. **Lighting Pattern:** The scene is bathed in "golden hour light" with a distinct "orange sky" and a "soft glow" visible across the landscape. The light is low-angled, creating "long warm shadows" cast by the trees and the hills, which is characteristic of the golden hour. 2. **Perspective:** The image uses a high-angle, wide-angle landscape perspective that captures the depth of the valley, the winding road, and th

Hard 100%vs100%
A portrait shot at 85mm f/1.4 with creamy bokeh background, fal/fal-ai/nano-banana-2PASS
A portrait shot at 85mm f/1.4 with creamy bokeh background, backlit with warm rim light separating the subject from a blurred garden

Evaluator

The image accurately reflects the technical specifications provided in the prompt: 1. **Perspective/Lens (85mm):** The image shows a classic portrait composition with a compression typical of an 85mm lens, focusing on the subject's face with a natural perspective. 2. **Depth of Field (f/1.4 with creamy bokeh):** The background is heavily blurred with a very shallow depth of field. The bokeh is smooth and "creamy," effectively isolating the subject from the garden background. 3. **Lighting (B

A street photograph with shallow depth of field as if shot afal/fal-ai/nano-banana-2PASS
A street photograph with shallow depth of field as if shot at 50mm f/1.8, subject sharp with soft city lights in the background

Evaluator

The image matches the prompt's requirements: 1. **Depth of Field:** The image exhibits a shallow depth of field. The subject (the man in the foreground) is sharp, while the background elements (cars, city lights, and buildings) are significantly blurred. This aligns with the "50mm f/1.8" specification. 2. **Lighting Pattern:** The background features soft, out-of-focus city lights (bokeh), which is consistent with the prompt's description of "soft city lights in the background." 3. **Perspec

A food photograph shot from above at 35mm f/2.8 with naturalfal/fal-ai/nano-banana-2PASS
A food photograph shot from above at 35mm f/2.8 with natural window light from the left, slight vignette, warm color temperature

Evaluator

To evaluate the image against the prompt: 1. **Perspective (Shot from above):** The image is a top-down (flat lay) perspective, which matches the "shot from above" requirement. 2. **Depth of Field (35mm f/2.8):** An f/2.8 aperture at 35mm would typically result in a shallow depth of field where certain parts of the table are blurred. In this image, most of the elements (the bread, the salad, the skillet, and the dip) are in sharp focus. The depth of field is quite deep, which is more characte

Extreme 100%vs100%
A tilt-shift photograph of a city street making real-life lofal/fal-ai/nano-banana-2PASS
A tilt-shift photograph of a city street making real-life look like a miniature model — selective focus strip, saturated colors

Evaluator

The image exhibits the following characteristics: 1. **Perspective/Tilt-Shift Effect:** The image successfully utilizes a "tilt-shift" effect. There is a very distinct selective focus strip where the center of the street is sharp, while the top (distant buildings) and the bottom (foreground rooftops) are heavily blurred. This creates the intended "miniature model" look. 2. **Depth of Field:** The depth of field is extremely shallow and controlled, mimicking the look of a macro lens used on a

A cinematic frame with blue and orange anamorphic lens flarefal/fal-ai/nano-banana-2PASS
A cinematic frame with blue and orange anamorphic lens flare streaking horizontally across a dark moody scene

Evaluator

The image features a dark, moody urban scene at night or during heavy rain. 1. **Lighting/Lens Flare**: There is a prominent horizontal light streak across the center of the frame. The colors transition from a bright blue on the left to a warm orange/yellow on the right, directly matching the "blue and orange anamorphic lens flare streaking horizontally" description. 2. **Perspective/Depth of Field**: The perspective is a street-level view looking down a wet road. The depth of field is relativ

A portrait with dramatic split lighting — half the face brigfal/fal-ai/nano-banana-2PASS
A portrait with dramatic split lighting — half the face brightly lit, the other half in deep shadow, high contrast chiaroscuro

Evaluator

The image is a black and white portrait of an elderly man. 1. **Lighting Pattern:** The image perfectly matches the description of "dramatic split lighting" and "high contrast chiaroscuro." The left side of the face (from the viewer's perspective) is brightly lit, while the right side is cast in deep, heavy shadow. The transition between light and shadow is sharp, creating a high-contrast effect. 2. **Perspective:** The perspective is a close-up portrait, which is standard for this type of lig

Color Precision100%vs92%
Easy 100%vs100%
A bright red sports car parked on a gray asphalt road — the fal/fal-ai/nano-banana-2PASS
A bright red sports car parked on a gray asphalt road — the red is vivid and unambiguous

Evaluator

The image shows a sports car that is a bright, vivid, and unambiguous red. The car is parked on a gray asphalt road. The colors match the prompt's requirements perfectly. VERDICT: PASS

A woman wearing a royal blue evening dress against a neutralfal/fal-ai/nano-banana-2PASS
A woman wearing a royal blue evening dress against a neutral background

Evaluator

The image shows a woman wearing a dress that is a vibrant, deep blue, which perfectly matches the description of "royal blue." The background is a textured, light beige/off-white color, which qualifies as a "neutral background." The colors in the image match the prompt exactly. VERDICT: PASS

A field of pure sunflower yellow flowers under a clear blue fal/fal-ai/nano-banana-2PASS
A field of pure sunflower yellow flowers under a clear blue sky

Evaluator

The image shows a vast field of bright yellow flowers under a clear, solid blue sky. The colors are consistent with the prompt's description of "pure sunflower yellow flowers" and a "clear blue sky." VERDICT: PASS

Medium 100%vs67%
A bedroom wall painted in #FF6B35 (burnt orange) with white fal/fal-ai/nano-banana-2PASS
A bedroom wall painted in #FF6B35 (burnt orange) with white furniture and natural daylight

Evaluator

The image shows a bedroom with a wall painted in a vibrant orange color. The hex code #FF6B35 represents a bright, saturated burnt orange/coral shade. The wall in the image matches this description of a saturated orange/burnt orange hue. The furniture (bed, nightstands, and dresser) is white, and the scene is illuminated by natural daylight coming from a large window. The color of the wall is a direct match for the requested color profile. VERDICT: PASS

A forest scene where the foliage is precisely #2D5F2D (dark fal/fal-ai/nano-banana-2PASS
A forest scene where the foliage is precisely #2D5F2D (dark muted green) with brown tree trunks

Evaluator

The image depicts a lush forest scene with a variety of green foliage and tall, textured tree trunks. The prompt specifies a very particular color for the foliage: **#2D5F2D (dark muted green)**. Looking at the image, the foliage consists of various shades of green, ranging from lighter, brighter greens in the sunlit areas to deeper, darker greens in the shadows. While the scene is generally green, the colors are natural and varied rather than being a single, precise hex-coded color. However

A room with walls in #4A90D9 (medium blue) with warm wooden fal/fal-ai/nano-banana-2PASS
A room with walls in #4A90D9 (medium blue) with warm wooden floor and white trim

Evaluator

The image shows a room with walls in a medium blue color, a warm wooden floor, and white trim (including the fireplace and window frames). 1. **Walls:** The walls are a medium blue, which aligns with the hex code #4A90D9 (a shade of medium blue). 2. **Floor:** The floor is made of warm-toned wood. 3. **Trim:** The trim around the window, the baseboards, and the fireplace is white. The colors in the image accurately match the descriptions and hex values provided in the prompt. VERDICT: PASS

Hard 100%vs100%
A minimalist room with walls in #F5E6CC (warm cream), a sofafal/fal-ai/nano-banana-2PASS
A minimalist room with walls in #F5E6CC (warm cream), a sofa in #2C3E50 (dark navy), and accent pillows in #E74C3C (bright red)

Evaluator

The image contains the following colors: - **Walls:** The walls are a warm cream color, which aligns with the requested **#F5E6CC**. - **Sofa:** The sofa is a dark navy blue, which aligns with the requested **#2C3E50**. - **Accent Pillows:** The pillows are a bright red, which aligns with the requested **#E74C3C**. All specified colors and hex values are accurately represented in the image. VERDICT: PASS

A product flat-lay on a #1A1A2E (deep dark blue) background,fal/fal-ai/nano-banana-2PASS
A product flat-lay on a #1A1A2E (deep dark blue) background, with a #F0C27F (soft gold) watch and #FFFFFF (pure white) earbuds

Evaluator

The image displays the following colors: 1. **Background:** A very dark, deep navy blue. The hex code #1A1A2E is a deep, dark blue, which matches the visual appearance of the background. 2. **Watch:** A soft gold color. The hex code #F0C27F is a soft gold/sand color, which matches the watch's appearance. 3. **Earbuds/Case:** Pure white. The hex code #FFFFFF is pure white, which matches the white earbuds and case. The colors in the image accurately reflect the specified hex values and descrip

A graphic design composition with background #FAFAFA (near-wfal/fal-ai/nano-banana-2PASS
A graphic design composition with background #FAFAFA (near-white), main shape #FF4500 (orange-red), and accent lines #333333 (dark charcoal)

Evaluator

The image contains the following colors: 1. **Background:** The background is a near-white color, consistent with the requested **#FAFAFA**. 2. **Main Shape:** The large organic shape is a vibrant orange-red, which matches the requested **#FF4500**. 3. **Accent Lines:** The thin, swirling lines are a dark charcoal/black color, consistent with the requested **#333333**. The colors in the image accurately reflect the hex values and descriptions provided in the prompt. VERDICT: PASS

Extreme 100%vs100%
A sunset sky gradient on a flat surface from #FF6B35 (orangefal/fal-ai/nano-banana-2PASS
A sunset sky gradient on a flat surface from #FF6B35 (orange) at the bottom to #1B1464 (deep indigo) at the top

Evaluator

The image shows a color gradient transitioning from a bright orange at the bottom to a deep, dark blue/indigo at the top. 1. **Bottom Color:** The bottom color is a vibrant orange. While it is difficult to verify an exact hex code without digital sampling, it visually aligns with the description of `#FF6B35` (a bright, saturated orange). 2. **Top Color:** The top color is a very dark, deep indigo/navy blue, which matches the description of `#1B1464`. 3. **Gradient Direction:** The gradient f

A smooth gradient on a wall going from #FF0000 (red) on the fal/fal-ai/nano-banana-2PASS
A smooth gradient on a wall going from #FF0000 (red) on the left to #0000FF (blue) on the right, transitioning evenly through purple

Evaluator

The image shows a smooth gradient on a wall. On the far left, the color is a bright red. As it moves toward the center, it transitions through a magenta/purple hue, and on the far right, it becomes a deep blue. This matches the description of a gradient from #FF0000 (red) to #0000FF (blue) transitioning through purple. VERDICT: PASS

A horizontal banner with a gradient from #00C9FF (cyan) on tfal/fal-ai/nano-banana-2PASS
A horizontal banner with a gradient from #00C9FF (cyan) on the left to #92FE9D (mint green) on the right

Evaluator

The image shows a horizontal banner with a gradient. 1. **Left side color:** The left side of the banner is a bright cyan/light blue. The hex code #00C9FF is a vibrant cyan, which matches the visual appearance of the left side of the banner. 2. **Right side color:** The right side of the banner is a light mint green. The hex code #92FE9D is a pale, bright mint/light green, which matches the visual appearance of the right side of the banner. 3. **Gradient direction:** The gradient flows horizon

Photorealism0%vs0%
Easy 0%vs0%
A single red sneaker on a clean white background with soft sfal/fal-ai/nano-banana-2FAIL
A single red sneaker on a clean white background with soft studio lighting and gentle shadow — product photography style

Evaluator

The image depicts a single red sneaker on a white background, which aligns with the prompt. However, upon closer inspection, there are several significant AI artifacts that prevent it from looking like a real studio photograph: 1. **Structural Anomalies:** The way the laces interact with the tongue and the upper part of the shoe is physically impossible. The laces appear to melt into the fabric of the shoe rather than being threaded through eyelets. 2. **Texture and Material Issues:** The tex

A ripe green apple on a seamless white background with soft fal/fal-ai/nano-banana-2FAIL
A ripe green apple on a seamless white background with soft side lighting and subtle shadow — catalog style

Evaluator

The image depicts a single green apple on a white background. Upon close inspection, there are several issues that prevent it from passing as a high-quality, real photograph: 1. **Artifacts and Texture:** The surface of the apple has a strange, "noisy" texture that looks more like digital noise or a poorly rendered texture than the natural skin of a fruit. There are small, white, speckled artifacts scattered across the surface that do not look like natural lenticels. 2. **Lighting and Shadow:

A clear glass perfume bottle on a reflective black surface wfal/fal-ai/nano-banana-2FAIL
A clear glass perfume bottle on a reflective black surface with studio lighting, no background distractions

Evaluator

The image shows a clear glass perfume bottle on a reflective black surface. Upon close inspection, there are several significant AI artifacts and physical inconsistencies: 1. **The Cap/Stopper:** The top of the bottle is highly irregular and nonsensical. The shape of the glass cap is asymmetrical, with strange, melted-looking geometry that does not follow the laws of physics or standard glass manufacturing. 2. **The Neck:** The transition between the cap and the bottle neck is poorly defined

Graphical design 92%vs42%

Data Visualisation100%vs0%
Easy 100%vs0%
A pie chart showing market share: Company A 35%, Company B 2fal/fal-ai/nano-banana-2PASS
A pie chart showing market share: Company A 35%, Company B 25%, Company C 20%, Others 20% — each slice a different color with labels and percentages

Evaluator

The chart is a pie chart as requested, with each slice a different color and labeled with the company name and percentage. The percentages shown are: Company A 35%, Company B 25%, Company C 20%, and Others 20% — which matches the prompt exactly. The labels are clearly readable, and the chart type is correct. The legend at the bottom also correctly maps colors to categories. VERDICT: PASS

A bar chart showing monthly sales for January through June wfal/fal-ai/nano-banana-2PASS
A bar chart showing monthly sales for January through June with values 12K, 18K, 15K, 22K, 19K, 25K — labeled axes, color-coded bars, and a title 'Monthly Sales 2025'

Evaluator

The chart is a bar chart showing monthly sales from January through June, with the exact values requested: 12K, 18K, 15K, 22K, 19K, 25K. Each bar is color-coded and labeled with its corresponding value. The x-axis is labeled “Month” with the months Jan through Jun, and the y-axis is labeled “Sales (in $K)” with appropriate scale. The title “Monthly Sales 2025” is present and correctly positioned. The chart type matches the requested bar chart format. All elements are clearly readable and correct

A simple line graph showing daily website visitors over one fal/fal-ai/nano-banana-2PASS
A simple line graph showing daily website visitors over one week (Mon-Sun): 1200, 1500, 1100, 1800, 2000, 1700, 1400 — with grid lines, axis labels, and title 'Weekly Traffic'

Evaluator

The chart is a line graph titled “Weekly Traffic,” with the x-axis labeled “Day of the Week” and the y-axis labeled “Number of Visitors,” including grid lines — all as requested. The data points correspond to the following values for Mon–Sun: - Monday: 1200 ✅ - Tuesday: 1500 ✅ - Wednesday: 1100 ✅ - Thursday: 1800 ✅ - Friday: 2000 ✅ - Saturday: 1700 ✅ - Sunday: 1400 ✅ All values are accurately plotted and readable. The chart type is a simple line graph, matching the request. VERDICT: PASS

Layout & Design89%vs11%
Easy 100%vs33%
A book club poster with an open book illustration, the titlefal/fal-ai/nano-banana-2PASS
A book club poster with an open book illustration, the title 'JOIN THE BOOK CLUB' prominently displayed, and 'Meets every Wednesday' as the tagline

Evaluator

The poster includes an open book illustration at its center, with the title “JOIN THE BOOK CLUB” prominently displayed at the top in large, stylized lettering. Below the book illustration, the tagline “Meets every Wednesday” is clearly visible and correctly placed at the bottom. The visual hierarchy is appropriate: the title is the largest and most dominant element, followed by the central illustration, and then the tagline. All text is readable, correctly positioned, and matches the prompt’s re

An event poster featuring a guitar illustration, the headlinfal/fal-ai/nano-banana-2PASS
An event poster featuring a guitar illustration, the headline 'LIVE MUSIC FEST' in large text, and 'Tickets available now' as a tagline below

Evaluator

The poster includes a large, stylized guitar illustration as the central visual element, which is clearly visible and prominent. The headline “LIVE MUSIC FEST” is displayed in large, bold, stylized text at the top, with the tagline “Tickets available now” directly beneath it in a smaller but still clearly readable font — both are correctly placed and follow the expected visual hierarchy. All text is readable, including the date, venue, headliners, open doors time, ticket URL, and social media

A movie night poster with a large popcorn image in the centefal/fal-ai/nano-banana-2PASS
A movie night poster with a large popcorn image in the center, the title 'MOVIE NIGHT' in bold at the top, and the tagline 'Every Friday at 8 PM' at the bottom

Evaluator

The poster features a large, centrally placed popcorn bucket, which fulfills the “large popcorn image in the center” requirement. The title “MOVIE NIGHT” is prominently displayed at the top in bold, illuminated lettering, matching the prompt. The tagline “EVERY FRIDAY AT 8 PM” is located at the bottom, within a decorative banner, and is clearly readable. The visual hierarchy is well established: the title commands attention at the top, the popcorn is the central focal point, and the tagline anc

Medium 67%vs0%
A landing page design with a hero header image at the top, afal/fal-ai/nano-banana-2PASS
A landing page design with a hero header image at the top, a headline and subtitle in the middle, a 'Sign Up' call-to-action button, and a footer with three social media icons

Evaluator

The image displays a landing page with the following elements: - Hero header image at the top: Present — a photo of people working in an office setting. - Headline and subtitle: Present — “UNLOCK YOUR POTENTIAL” as the headline, with “Achieve More, Faster. Join thousands of creators using Elevate to build their future today.” as the subtitle, both centered and clearly readable. - “Sign Up” call-to-action button: Present — a teal button with white text, positioned below the subtitle, following s

A newsletter layout with a banner image header, a two-columnfal/fal-ai/nano-banana-2FAIL
A newsletter layout with a banner image header, a two-column body section with text on the left and an image on the right, a highlighted quote block, and a footer with unsubscribe link

Evaluator

The image displays a newsletter layout that closely matches the described structure: - Banner image header: Present at the top with the title “THE INNOVATION EDGE” and issue details. - Two-column body section: The left column contains text (article content with headings and bullet points), and the right column contains an image with a caption (“DRIVING SUCCESS WITH DATA-DRIVEN INSIGHTS”). - Highlighted quote block: Present at the bottom of the main content area with a quote and attribution. - F

A restaurant menu layout with a logo header, three category fal/fal-ai/nano-banana-2PASS
A restaurant menu layout with a logo header, three category sections (appetizers, mains, desserts) each with items and prices, and a footer with address and hours

Evaluator

All described layout zones/elements are present: - Logo header: “THE OAK KITCHEN” with “FARM TO TABLE | EST. 2018” beneath it, centered at the top. - Three category sections: “APPETIZERS”, “MAIN ENTREES”, and “DESSERTS”, each clearly labeled and visually separated. - Items and prices: Each dish has a name, description, and price, correctly aligned and readable. - Footer: Contains address (“123 FOREST AVE, OAKSVILLE, CA 90210”), phone number, website, and operating hours, all clearly legible and

Hard 100%vs0%
A mobile app UI mockup showing a dashboard with a top navigafal/fal-ai/nano-banana-2PASS
A mobile app UI mockup showing a dashboard with a top navigation bar, a search field, a 2x2 grid of feature cards with icons, a list of recent activity items, and a bottom tab bar

Evaluator

All described layout zones/elements are present with correct visual hierarchy: - Top navigation bar: The status bar at the top shows time (9:41) and connectivity icons, and the app title “NEXUS” is prominently displayed. - Search field: A search bar with placeholder text “Search features, transactions...” is clearly visible below the welcome message. - 2x2 grid of feature cards: Four cards (“PAYMENTS”, “BUDGETS”, “PROJECTS”, “REPORTS”) are arranged in a 2x2 grid with icons and descriptive text.

A magazine double-page spread with a left page containing a fal/fal-ai/nano-banana-2PASS
A magazine double-page spread with a left page containing a large hero photo, and a right page with a two-column article, a pull quote, a sidebar with author bio, and a page number

Evaluator

The image shows a magazine double-page spread. The left page features a large hero photo of a woman hiking with a scenic mountain backdrop, overlaid with the title “THE ART OF URBAN EXPLORATION” and subtitle “FINDING ADVENTURE BEYOND THE TRAILHEAD.” This matches the prompt’s description of a large hero photo on the left. The right page contains: - A two-column article layout with the main headline “Rediscovering the City: A New Era of Travel” and subheadings (“A New Narrative,” “The Authentic E

A fashion magazine spread with a full-bleed left-page photo,fal/fal-ai/nano-banana-2PASS
A fashion magazine spread with a full-bleed left-page photo, right page with three-column layout, headline, body copy, a smaller inset image, and styled page numbers

Evaluator

The image depicts a fashion magazine spread that closely matches the described layout: - Left page: Full-bleed photo of a model in an urban setting — ✅ Present. - Right page: Three-column layout — ✅ Present (three distinct columns of text: “THE LOOK”, “ACCESSORIES”, “MODERN LUXURY”). - Headline: “URBAN ELEGANCE” with subheading “THE ART OF AUTUMN STYLE” — ✅ Present, prominent, and correctly placed at the top. - Body copy: Three columns of placeholder text (Lorem ipsum) — ✅ Present, correctly pl

Style Diversity92%vs75%
Easy 100%vs67%
A golden retriever sitting in a garden, painted in the stylefal/fal-ai/nano-banana-2PASS
A golden retriever sitting in a garden, painted in the style of an oil painting with visible brushstrokes and rich texture

Evaluator

The image depicts a golden retriever sitting in a lush garden, surrounded by vibrant flowers and foliage, with a stone pathway and an arched trellis in the background. The style is clearly that of an oil painting: there are visible brushstrokes, especially in the foliage, sky, and textured surfaces like the stone path and dog’s fur. The colors are rich and layered, with a painterly quality that suggests impasto or thick application of paint. The composition and lighting also evoke traditional oi

A golden retriever sitting in a garden, rendered in pixel arfal/fal-ai/nano-banana-2PASS
A golden retriever sitting in a garden, rendered in pixel art style with a 32x32 grid and limited color palette

Evaluator

The image depicts a golden retriever sitting in a garden, rendered in a pixel art style. The visual characteristics of pixel art are clearly present: individual pixels form the shapes, edges are blocky and defined, and the image uses a limited color palette with distinct, saturated hues. The 32x32 grid resolution is not explicitly verifiable from the image alone, but the pixelated aesthetic is consistent with that scale. The subject and setting match the prompt. VERDICT: PASS

A golden retriever sitting in a garden, rendered in Japanesefal/fal-ai/nano-banana-2PASS
A golden retriever sitting in a garden, rendered in Japanese anime style with flat colors and large expressive eyes

Evaluator

The image depicts a golden retriever sitting in a garden setting that strongly resembles a Japanese garden, complete with cherry blossoms, a red arched bridge, a stone path, a pagoda-style building, and traditional landscaping. The art style is clearly Japanese anime-inspired: the dog has large, expressive, cartoonish eyes, simplified facial features, and a cheerful, stylized expression. The coloring is flat with bold outlines, consistent with anime conventions. While the dog’s fur has some shad

Medium 100%vs100%
A woman with a parasol in the style of Impressionism — soft fal/fal-ai/nano-banana-2PASS
A woman with a parasol in the style of Impressionism — soft brushstrokes, dappled light, pastel palette

Evaluator

The image clearly depicts a woman holding a parasol in a lush garden, rendered with visible, loose brushstrokes that suggest movement and texture. The palette is dominated by soft pastels — light blues, pinks, greens, and yellows — consistent with Impressionist aesthetics. Dappled light is evident in the way sunlight filters through foliage, creating patches of brightness and shadow on the path and figures. The overall composition and rendering align with the requested Impressionist style. VERD

A city street scene in the style of Art Deco — geometric shafal/fal-ai/nano-banana-2PASS
A city street scene in the style of Art Deco — geometric shapes, gold and black palette, ornamental symmetry

Evaluator

The image clearly embodies the requested Art Deco style. Key visual characteristics are unmistakably present: - **Geometric shapes**: Buildings feature sharp angles, stepped forms, zigzags, and repeating patterns — hallmarks of Art Deco architecture. - **Gold and black palette**: The dominant color scheme is warm golds and deep blacks, creating a luxurious, dramatic contrast. - **Ornamental symmetry**: The composition is highly symmetrical, with buildings mirroring each other across the street,

A portrait of a man in Pop Art style — bold outlines, Ben-Dafal/fal-ai/nano-banana-2PASS
A portrait of a man in Pop Art style — bold outlines, Ben-Day dots, flat vivid primary colors

Evaluator

The image clearly embodies the requested Pop Art style. It features: - Bold, black outlines defining all shapes and forms. - Ben-Day dots (a hallmark of Pop Art) used to create shading and texture, especially on the face and hair. - Flat, vivid primary colors: red, blue, yellow, and white dominate the palette. - A stylized, graphic composition with a background of large, colorful circles — a classic Pop Art motif. All key visual characteristics of the requested style are present and unmistakab

Hard 67%vs33%
A woman in a futuristic city rendered in cyberpunk Art Nouvefal/fal-ai/nano-banana-2PASS
A woman in a futuristic city rendered in cyberpunk Art Nouveau — neon colors and tech elements combined with flowing organic lines and floral borders

Evaluator

The image successfully embodies the requested “cyberpunk Art Nouveau” style by merging neon colors, tech elements, flowing organic lines, and floral motifs. The woman’s outfit and the surrounding architecture feature intricate, curvilinear designs reminiscent of Art Nouveau, while glowing neon signs, flying vehicles, and circuit-like patterns establish the cyberpunk aesthetic. Floral borders and motifs are integrated throughout the composition, including in the railings, the title frame, and the

A forest rendered in photorealistic watercolor — the detail fal/fal-ai/nano-banana-2PASS
A forest rendered in photorealistic watercolor — the detail and lighting of a photo combined with visible watercolor bleeds and paper texture

Evaluator

The image clearly attempts to render a forest in a style described as “photorealistic watercolor.” It incorporates visible watercolor bleeds — especially in the background foliage and around the edges — and shows paper texture, particularly along the borders and in the white margins. The lighting and detail are rendered with photographic realism: the sunbeams filtering through the trees, the nuanced shadows, the texture of bark, leaves, and ferns, and the depth of field are all consistent with p

A medieval castle depicted in Japanese ukiyo-e woodblock prifal/fal-ai/nano-banana-2FAIL
A medieval castle depicted in Japanese ukiyo-e woodblock print style combined with photorealistic sky and lighting

Evaluator

The image attempts to merge a medieval castle with ukiyo-e aesthetics, but the result is not clearly recognizable as either style in a coherent or authentic way. Key issues: - The castle architecture is rendered in a detailed, realistic, Western medieval style — not stylized or simplified as in ukiyo-e. - The sky and lighting are photorealistic in their rendering of clouds, sun rays, and reflections on water — which is the second part of the prompt — but this photorealism clashes with the flat,

Extreme 100%vs100%
An interior scene rendered in soft brutalism — raw concrete fal/fal-ai/nano-banana-2PASS
An interior scene rendered in soft brutalism — raw concrete textures combined with rounded pastel furniture and warm diffused light

Evaluator

The image clearly embodies the requested “soft brutalism” style. Key visual characteristics are present: - **Raw concrete textures**: Exposed concrete walls, ceiling, and floor dominate the space, showcasing the unpolished, industrial aesthetic of brutalism. - **Rounded pastel furniture**: The pink sofa, lavender ottoman, and sage-green armchair are soft, rounded, and rendered in pastel tones — directly matching the prompt. - **Warm diffused light**: Natural light streams through the large wind

A still life painted in anxious minimalism — sparse compositfal/fal-ai/nano-banana-2PASS
A still life painted in anxious minimalism — sparse composition with uncomfortable negative space, muted colors, and subtle visual tension

Evaluator

The image presents a still life with a sparse composition: only a bowl, a single dark fruit, and a spoon are arranged on a wooden surface against a large, textured, muted gray background. The negative space is substantial and deliberately uncluttered, creating a sense of quiet isolation. The color palette is restrained — mostly grays, browns, and off-whites — fitting the “muted colors” requirement. The brushwork is visible and textured, suggesting a painted medium, and the objects are rendered w

A cityscape rendered in nostalgic futurism — retro-futuristifal/fal-ai/nano-banana-2PASS
A cityscape rendered in nostalgic futurism — retro-futuristic 1960s space-age aesthetics with a melancholic warm-toned patina

Evaluator

The image clearly embodies the requested “nostalgic futurism — retro-futuristic 1960s space-age aesthetics with a melancholic warm-toned patina.” Key visual characteristics are present: - **Retro-futurism**: The architecture features sleek, optimistic, mid-century modernist forms — domed towers, curved spires, and elevated transit systems — reminiscent of 1960s sci-fi visions (e.g., “Tomorrowland” or “Metropolis”). - **Warm-toned patina**: The entire scene is bathed in a golden-orange, sunset-l