192 evaluations across 6 categories
Benchmark V1 verdicts are produced by VLM judges and can contain mistakes. Treat PASS/FAIL labels as machine-assisted assessments, and inspect the images yourself. Learn more about the methodology.
Source-backed model context, size, cost, and request settings for this ImageBench V1 run.
FLUX.2 Max is Black Forest Labs' higher-capacity FLUX.2 tier, described as a top-end generation model with support for stronger visual output and, when prompted, grounding search for current visual context.
Reve 2.1 is Reve AI's flagship text-to-image model, generating natively at 4K (4096x4096) with layout intelligence — it reasons about structure and spatial hierarchy before generating. It is a standout at in-image typography (including foreign scripts) and ranks #2 on the Text-to-Image Arena, well suited to posters, packaging, and marketing design. The older fal-ai/reve/text-to-image endpoint serves the earlier Reve Image 1.0.
On ImageBench V1 (192 prompts, 6 categories), Flux 2 Max scores 61.9 overall with a 67.2% task pass rate, while Reve 2.1 scores 74.8 overall with a 79.7% pass rate. The biggest difference is human realism (hands, faces, anatomy): Flux 2 Max passes 45.2% of those prompts vs 66.7% for Reve 2.1. Flux 2 Max is an API model (from $0.07 / image); Reve 2.1 is an API model ($0.04 / image).
Reve 2.1 is better overall on ImageBench V1, scoring 74.8 vs 61.9. Flux 2 Max is strongest at text rendering (93.3%). Reve 2.1 is strongest at text rendering (100%).
Yes — on the Human realism category of ImageBench V1, Flux 2 Max passes 45.2% of prompts and Reve 2.1 passes 66.7%. That is the largest per-category difference between Flux 2 Max and Reve 2.1.
The ImageBench gallery shows Flux 2 Max and Reve 2.1 outputs for the same 192 prompts side by side, filterable by category and difficulty — the fastest way to judge them with your own eyes instead of trusting aggregate scores. Open them in the gallery.