whatmodel.sh / image / FLUX.2 [pro]
FLUX.2 [pro]
↗ share
+ contribute
FLUX.2 [pro] is a closed-weights image model from Black Forest Labs, released November 2025. Licence: proprietary.
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of FLUX.2 [pro], out of 197 with a score, then more from Black Forest Labs.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 34 |  Reve V1.5 | 63±3 | comparison only | ||
| 35 |  Cosmos3-Super-Text2Image | 63±2 | local | ||
| 36 | FLUX.2 [pro] | 63±2 | api $0.030/image | ||
| 37 | FLUX.2 [flex] | 62±2 | api $0.050/image | ||
| 38 |  HunyuanImage 3.0-Instruct | 62±3 | api $0.090/image +local | ||
| more from Black Forest Labs | |||||
| 32 | FLUX.2 [max] | 64±1 | api $0.070/image | ||
| 61 | FLUX.2 [dev] | 58±1 | api $0.046/image +local | ||
| 81 | FLUX.2 [klein] Base 9B | 55±4 | comparison only | ||
$ what it's good at
text to image▂▅▅▃▄▄█▃▁▂▁▁ #27 of 126 · 63% of its score · 3 tests
Beats Seedream 4.5, Wan 2.7 Image Pro, Cosmos3-Super-Text2Image here, though they rank higher overall. Trails FLUX.2 [flex] here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena text-to-image | 1153.3 ✎ | ▂▂▃▄▇█▄▂▄▂·▂ beats 47/75 | 49% |
| ImageTime (prompt-only, overall) | 61.0% ✎ | ▄·····▄█▄·▄█ beats 4/7 | 10% |
| Qwen-Image-Bench (Q-Judger, v1) | 54.6% ✎ | █▅▅·▅▅█·█··▃ beats 8/17 | 5.2% |
image to image / editing▁▁·▃▂▃█▃▃▄▁▁ #27 of 62 * · 28% of its score · 2 tests
Trails Wan 2.7 Image, HunyuanImage 3.0-Instruct here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena image edit | 1245.4 ✎ | ▂▁▁▂▆▇█▄▆▅▁▂ beats 21/53 | 18% |
| GEBench GUI state generation (English GE-Score) | 51.2% ✎ | ▄▄····▄▄█▄·█ beats 4/8 | 9.3% |
other tests1 not in a task · 7.6% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Rapidata Benchmark.ai image benchmark (overall Elo) | 1003.4 ✎ | ▁▁▁▄▂█▂▁▁▂▁▁ beats 18/34 | 7.6% |
$ where to run it
Through an API
api · $0.030/image · docs.bfl.ai ↗ · price sourceUSD for a text-to-image output of up to 1 megapixel (the first-megapixel rate; each additional output megapixel adds $0.015; image editing starts at $0.045). Matches the "from $0.03" text-to-image figure in the BFL API docs (1 credit = $0.01). Product: BFL API. API model: flux-2-pro. Settings: output <=1 MP (e.g. 1024×1024), no input images, single image. Price basis: published first-megapixel list rate. Currency: USD. Black Forest Labs official pricing page, observed 2026-09-25.
$ how the score was worked out · LMArena leaderboard dataset 67%, Can Image Models Imagine Time… 10%, GEBench: Benchmarking Image G… 9% and 2 more
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 LMArena leaderboard dataset | 2 | 67% |
 Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal Consistency | 1 | 10% |
| GEBench: Benchmarking Image Generation Models as GUI Environments | 1 | 9% |
 Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings | 1 | 8% |
| Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation | 1 | 5% |
| prior · pull toward the middle | 1% | |
| weighted average | = 62.7 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json