whatmodel.sh / image / Reve 2.1
Reve 2.1
↗ share
+ contribute
Reve 2.1 is a closed-weights image model from Reve, released July 2026. Licence: proprietary.
Catalogue identity notes
Comparison-only. Arena text_to_image entry 'reve-2.1' (reve, Proprietary), first listed 2026-07-09.
Model information sources
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of Reve 2.1, out of 197 with a score, then more from Reve.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 5 |  Nano Banana 2.1 | 81±2 | api $0.034/image | ||
| 6 |  Grok Imagine Image 2.0 | 79±2 | api $0.040/image | ||
| 7 | Reve 2.1 | 78±2 | api $0.25/image | ||
| 8 |  Muse Image | 76±2 | api $0.010/image | ||
| 9 | Nano Banana 2 (Gemini 3.1 Flash Image) | 76±1 | api $0.067/image | ||
| more from Reve | |||||
| 13 | Reve 2.0 | 74±2 | api $0.25/image | ||
| 34 | Reve V1.5 | 63±3 | comparison only | ||
| 44 | Reve V1.1 | 61±4 | comparison only | ||
$ what it's good at
text to image▂▅▅▃▄▄█▃▁▃▁▁ #5 of 126 * · 64% of its score · 1 test
Beats Grok Imagine Image 2.0 here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena text-to-image | 1301.7 ✎ | ▂▂▃▄▇█▄▂▄▃·▂ beats 70/75 | 64% |
image to image / editing▁▁·▃▂▃█▃▃▄▁▁ #11 of 62 * · 24% of its score · 1 test
Trails ChatGPT Image Latest (chatgpt-image-latest), Seedream 5.0 Pro, Nano Banana Pro (Gemini 3 Pro Image) here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena image edit | 1374.3 ✎ | ▂▁▁▂▆▇█▄▆▅▁▂ beats 41/53 | 24% |
other tests1 not in a task · 10% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Rapidata Benchmark.ai image benchmark (overall Elo) | 1147.5 ✎ | ▁▁▁▄▂█▂▁▁▃▁▁ beats 31/34 | 10% |
$ where to run it
Through an API
api · fal.ai · $0.25/image · fal.ai ↗ · price sourceUSD per generated image: fal bills reve/2.1/text-to-image at $0.25 per image (billing unit images), flat across aspect ratios. Product: fal.ai partner API (Reve's model served through fal). API model: reve/2.1/text-to-image (Reve 2.1). Settings: text-to-image, default aspect ratio, one image. Price basis: published per-image list rate. The fal endpoint is live but unlisted in fal's catalogue (status unlisted, published 2026-07-14, not deprecated). Not a Reve direct tariff (Reve's own pricing page did not render a public API price). Currency: USD. fal.ai official model page, observed 2026-09-25.
$ how the score was worked out · LMArena leaderboard dataset 88%, Rapidata/text-to-image-human-… 10%
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 | 88% |
 Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings | 1 | 10% |
| prior · pull toward the middle | 2% | |
| weighted average | = 77.8 |
$ 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