GPT-Image-2.6 Flare (Medium)
OpenAIProprietary
GPT-Image-2.6 Flare (Medium) is an AI image model from OpenAI. On LMArena’s Text-to-image leaderboard it ranks 4 of 84 with 1383±13 from 2,552 votes. On LMArena’s Image editing leaderboard it ranks 6 of 63 with 1460±10 from 3,558 votes. License: Proprietary.
Key figures
- Developer
- OpenAI
- License
- Proprietary
Not yet available: Released (per AA), AA Elo
Who it is for (from the data)
- Best-quality seekers: #4 of 84 on Text-to-image, in the top 10.
- Generating and editing images: it is ranked on both boards.
- Use via OpenAI's service or API: LMArena lists it as proprietary.
- Existing OpenAI users: this vendor has 9 models on Text-to-image.
Neighbours on Text-to-image
| # | Model | Score | Votes | AA Elo | License | Δ |
|---|---|---|---|---|---|---|
| 1 | GPT-Image-2.5 Sunburst OpenAI | 1428 | 58,604 | 1223 | Proprietary | +45 |
| 2 | GPT-Image-2.6 Sunburst (Medium) OpenAI | 1406 | 2,720 | – | Proprietary | +23 |
| 3 | GPT-Image-2.5 Flare OpenAI | 1400 | 57,645 | 1207 | Proprietary | +17 |
| 4 | GPT-Image-2.6 Flare (Medium) OpenAI | 1383 | 2,552 | – | Proprietary | |
| 5 | GPT-Image-2 (Medium) OpenAI | 1382 | 106,289 | 1189 | Proprietary | -1 |
| 6 |  MAI-Image-2.6 Microsoft AI | 1330 | 38,967 | 1167 | Proprietary | -53 |
| 7 |  Gemini Nano Banana 2.1 Google | 1328 | 4,966 | 1176 | Proprietary | -55 |
Alternatives · More from OpenAI
| # | Model | Score | Votes | AA Elo | License |
|---|---|---|---|---|---|
| 1 | GPT-Image-2.5 Sunburst OpenAI | 1428 | 58,604 | 1223 | Proprietary |
| 2 | GPT-Image-2.6 Sunburst (Medium) OpenAI | 1406 | 2,720 | – | Proprietary |
| 3 | GPT-Image-2.5 Flare OpenAI | 1400 | 57,645 | 1207 | Proprietary |
| 5 | GPT-Image-2 (Medium) OpenAI | 1382 | 106,289 | 1189 | Proprietary |
| 19 | GPT-Image-1.5 (High Fidelity) OpenAI | 1236 | 169,494 | 1123 | Proprietary |
Alternatives · Top open-weight models
| # | Model | Score | Votes | AA Elo | License |
|---|---|---|---|---|---|
| 21 |  Qwen-Image-2.1 Alibaba | 1227 | 17,883 | 1043 | qwen-research |
| 22 |  Ideogram 4.0 (Quality) Ideogram | 1199 | 77,744 | 1025 | Ideogram Open Model |
| 29 |  Cosmos3-Super-Text2Image (Agentic) NVIDIA | 1164 | 10,161 | 993 | OpenMDW-1.1 |
| 35 |  HunyuanImage 3.0 Tencent | 1152 | 175,294 | 932 | tencent-hunyuan-community |
| 36 | Cosmos3-Super-Text2Image NVIDIA | 1150 | 17,448 | 986 | OpenMDW-1.1 |
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 GPT-Image-2.6 Flare (Medium) rank among AI image models?
Text-to-image rank 4 (1383); Image editing rank 6 (1460) (LMArena, data as of Nov 10, 2026).
Is GPT-Image-2.6 Flare (Medium) open-weight?
No. LMArena lists it as Proprietary; it is available only through OpenAI’s products or API.
Can GPT-Image-2.6 Flare (Medium) edit images?
Yes. GPT-Image-2.6 Flare (Medium) is #6 of 63 on the LMArena image-edit board (1460, 3,558 votes).
Who makes GPT-Image-2.6 Flare (Medium)?
According to LMArena, GPT-Image-2.6 Flare (Medium) is made by OpenAI.
How reliable is GPT-Image-2.6 Flare (Medium)'s score?
The scores are based on 2,552 votes on Text-to-image (95% CI ±13); 3,558 votes on Image editing (95% CI ±10). More votes and narrower intervals mean a more stable rank.
How far is GPT-Image-2.6 Flare (Medium) from #1 on Text-to-image?
#1 on Text-to-image is GPT-Image-2.5 Sunburst (1428); GPT-Image-2.6 Flare (Medium) scores 1383, 45 points behind.
Sources
LMArena Text-to-image data published on Nov 8, 2026.
LMArena Image editing data published on Nov 9, 2026.
17NAS syncs the upstream leaderboards daily; this page's data was synced on Nov 10, 2026.
Price, resolution and speed have no reliable public data yet and are omitted; all values come from the snapshot, blanks show –.