GPT-Image-2 (Medium)
OpenAIProprietary
GPT-Image-2 (Medium) is an AI image model from OpenAI. On LMArena’s Text-to-image leaderboard it ranks 3 of 82 with 1383±4 from 93,334 votes. On LMArena’s Image editing leaderboard it ranks 3 of 60 with 1461±3 from 328,307 votes. License: Proprietary.
Key figures
- Developer
- OpenAI
- License
- Proprietary
- Released (per AA)
- Apr 2026
Who it is for (from the data)
- Best-quality seekers: #3 of 82 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 7 models on Text-to-image.
Neighbours on Text-to-image
| # | Model | Score | Votes | AA Elo | License | Δ |
|---|---|---|---|---|---|---|
| 1 | GPT Image 2.5 Sunburst OpenAI | 1425 | 17,752 | 1222 | Proprietary | +42 |
| 2 | GPT Image 2.5 Flare OpenAI | 1398 | 16,889 | 1207 | Proprietary | +15 |
| 3 | GPT Image 2 (Medium) OpenAI | 1383 | 93,334 | 1186 | Proprietary | |
| 4 |  Grok Imagine Image 2.0 (Canvas) xAI | 1334 | 3,113 | – | Proprietary | -49 |
| 5 |  MAI Image 2.6 Microsoft AI | 1332 | 25,091 | 1166 | Proprietary | -51 |
| 6 |  Gemini Nano Banana 2.1 Google | 1328 | 5,310 | 1176 | Proprietary | -55 |
| 7 |  Reve 2.1 Reve | 1302 | 8,249 | – | Proprietary | -81 |
Alternatives · More from OpenAI
| # | Model | Score | Votes | AA Elo | License |
|---|---|---|---|---|---|
| 1 | GPT Image 2.5 Sunburst OpenAI | 1425 | 17,752 | 1222 | Proprietary |
| 2 | GPT Image 2.5 Flare OpenAI | 1398 | 16,889 | 1207 | Proprietary |
| 17 | GPT Image 1.5 High Fidelity OpenAI | 1237 | 169,927 | – | Proprietary |
| 49 | GPT Image 1 OpenAI | 1116 | 268,453 | 1013 | Proprietary |
| 54 | GPT Image 1 Mini OpenAI | 1110 | 171,058 | 936 | 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 GPT-Image-2 (Medium) rank among AI image models?
Text-to-image rank 3 (1383); Image editing rank 3 (1461) (LMArena, data as of Oct 26, 2026).
Is GPT-Image-2 (Medium) open-weight?
No. LMArena lists it as Proprietary; it is available only through OpenAI’s products or API.
Can GPT-Image-2 (Medium) edit images?
Yes. GPT-Image-2 (Medium) is #3 of 60 on the LMArena image-edit board (1461, 328,307 votes).
Who makes GPT-Image-2 (Medium)?
According to LMArena, GPT-Image-2 (Medium) is made by OpenAI.
How reliable is GPT-Image-2 (Medium)'s score?
The scores are based on 93,334 votes on Text-to-image (95% CI ±4); 328,307 votes on Image editing (95% CI ±3). More votes and narrower intervals mean a more stable rank.
How far is GPT-Image-2 (Medium) from #1 on Text-to-image?
#1 on Text-to-image is GPT Image 2.5 Sunburst (1425); GPT-Image-2 (Medium) scores 1383, 42 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 –.