FLUX 1 Dev FP8
LMArena ID: flux-1-dev-fp8
Black Forest LabsOpenOpen
FLUX 1 Dev FP8 is an AI image model from Black Forest Labs. On LMArena’s Text-to-image leaderboard it ranks 78 of 82 with 969±4 from 49,221 votes. It is not on LMArena’s Image editing leaderboard yet. License: Open.
Key figures
- Developer
- Black Forest Labs
- License
- Open
Not yet available: Released (per AA), LMArena · Image editing, AA Elo
Who it is for (from the data)
- When quality is not the top priority: #78 of 82 on Text-to-image, in the bottom half; if quality matters most, check higher-ranked models first.
- Mainly text-to-image: no image-edit results yet.
- Self-hosting or on-premise use: LMArena lists its license as Open.
- Existing Black Forest Labs users: this vendor has 11 models on Text-to-image.
Neighbours on Text-to-image
| # | Model | Score | Votes | AA Elo | License | Δ |
|---|---|---|---|---|---|---|
| 75 | LLucid Origin Leonardo.Ai | 1013 | 287,341 | – | Proprietary | +44 |
| 76 |  GLM Image Z.ai | 1012 | 4,854 | 885 | MIT | +43 |
| 77 |  Gemini 2.0 Flash Preview Image Generation Google | 975 | 257,227 | – | Proprietary | +6 |
| 78 | FLUX 1 Dev FP8 Black Forest Labs | 969 | 49,221 | – | Open | |
| 79 |  DALL·E 3 OpenAI | 968 | 238,743 | – | Proprietary | -1 |
| 80 | FLUX 1 Kontext Dev Black Forest Labs | 941 | 216,225 | – | flux-1-dev-non-commercial-license | -28 |
| 81 | ?Stable Diffusion 3.5 Large | 938 | 23,396 | – | Open | -31 |
Alternatives · More from Black Forest Labs
| # | Model | Score | Votes | AA Elo | License |
|---|---|---|---|---|---|
| 29 | FLUX 2 Max Black Forest Labs | 1162 | 123,203 | – | Proprietary |
| 30 | FLUX 2 Flex Black Forest Labs | 1157 | 156,923 | – | Proprietary |
| 32 | FLUX 2 Pro Black Forest Labs | 1153 | 212,359 | – | Proprietary |
| 38 | FLUX 2 Dev Black Forest Labs | 1146 | 77,988 | – | flux-non-commercial-license |
| 61 | FLUX 1 Kontext Max Black Forest Labs | 1074 | 65,510 | – | Proprietary |
Alternatives · Top open-weight models
| # | Model | Score | Votes | AA Elo | License |
|---|---|---|---|---|---|
| 19 |  Qwen Image 2.1 Alibaba | 1223 | 11,441 | 1042 | qwen-research |
| 20 |  Ideogram 4.0 Quality Ideogram | 1205 | 60,591 | – | Ideogram Open Model |
| 27 |  Cosmos3-Super-Text2Image (Agentic) NVIDIA | 1165 | 10,805 | – | OpenMDW-1.1 |
| 33 | Cosmos3-Super-Text2Image NVIDIA | 1152 | 18,485 | – | OpenMDW-1.1 |
| 35 |  Hunyuan Image 3.0 Tencent | 1150 | 180,518 | 989 | tencent-hunyuan-community |
How to read the scores
- LMArena score: people blind-pick the better of two anonymous images for the same prompt, and the votes are fitted into an Elo-style rating; "±" is the 95% confidence interval.
- Text-to-image and image edit are separate boards, so scores are not comparable across them; AA Elo comes from Artificial Analysis on a different scale.
- If the gap between two models is smaller than their combined intervals, the order is not statistically reliable; treat them as the same tier. More votes mean narrower intervals.
FAQ
Where does FLUX 1 Dev FP8 rank among AI image models?
Text-to-image rank 78 (969) (LMArena, data as of Oct 26, 2026).
Is FLUX 1 Dev FP8 open-weight?
LMArena lists its license as Open (not proprietary); check the license text for commercial-use terms.
Can FLUX 1 Dev FP8 edit images?
The LMArena image-edit board has no result for FLUX 1 Dev FP8 yet, so we cannot confirm its editing ability from the data.
Who makes FLUX 1 Dev FP8?
According to LMArena, FLUX 1 Dev FP8 is made by Black Forest Labs.
How reliable is FLUX 1 Dev FP8's score?
The scores are based on 49,221 votes on Text-to-image (95% CI ±4). More votes and narrower intervals mean a more stable rank.
How far is FLUX 1 Dev FP8 from #1 on Text-to-image?
#1 on Text-to-image is GPT Image 2.5 Sunburst (1425); FLUX 1 Dev FP8 scores 969, 456 points behind.
Sources
LMArena Text-to-image data published on Oct 7, 2026.
LMArena Image editing data published on Oct 20, 2026.
17NAS syncs the upstream leaderboards daily; this page's data was synced on Oct 26, 2026.
Price, resolution and speed have no reliable public data yet and are omitted; all values come from the snapshot, blanks show –.