Vision · Style Control · Entity Recognition
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 1,291.657 |
| 2 | Gemini 3 Flash | 1,290.0107 |
| 3 | Gemini 3.1 Pro Preview | 1,283.9787 |
| 4 | Gemini 3 Flash (Minimal) | 1,273.9397 |
| 5 | Gemini 3.1 Flash-Lite Preview | 1,271.1111 |
| 6 | GPT-5 (High) | 1,261.4765 |
| 7 | Gemini 2.5 Pro | 1,250.8092 |
| 8 | Claude Opus 4.7 (High) | 1,242.3894 |
| 9 | GPT-5.2 Chat (20260210) | 1,238.8751 |
| 10 | Grok 4.20 Beta (Reasoning, 0309) | 1,238.1142 |
| 11 | Claude Opus 4.6 | 1,236.5651 |
| 12 | Grok 4 (0709) | 1,236.1557 |
| 13 | Claude Opus 4.6 (High) | 1,235.8476 |
| 14 | Kimi K2.5 (Thinking) | 1,232.3344 |
| 15 | o3 (2025-04-16) | 1,231.4361 |
| 16 | GPT-5.1 (High) | 1,228.2256 |
| 17 | Grok 4.20 Multi-Agent Beta (0309) | 1,226.5086 |
| 18 | Gemini 2.5 Flash | 1,221.3147 |
| 19 | GPT-5.5 (High) | 1,219.1786 |
| 20 | GPT-5.5 | 1,218.5757 |
| 21 | o4-mini (2025-04-16) | 1,218.556 |
| 22 | ChatGPT-4o Latest (20250326) | 1,218.1401 |
| 23 | Grok 4.1 Fast (Reasoning) | 1,216.6141 |
| 24 | GPT-5.4 | 1,215.376 |
| 25 | Qwen3.5-397B-A17B | 1,211.3363 |
| 26 | GPT-5 mini (High) | 1,211.1918 |
| 27 | Grok 4.3 | 1,209.5504 |
| 28 | GPT-5.2 (High) | 1,201.2996 |
| 29 | GPT-5.4 mini (High) | 1,198.1449 |
| 30 | GPT-4.1 mini (2025-04-14) | 1,196.7441 |
| 31 | Gemma 4 31B | 1,196.1957 |
| 32 | GPT-5.4 (High) | 1,196.1683 |
| 33 | GPT-5 Chat | 1,190.3673 |
| 34 | GPT-5.1 | 1,186.9041 |
| 35 | GPT-4.1 (2025-04-14) | 1,184.0948 |
| 36 | Claude Opus 4.7 | 1,183.9539 |
| 37 | Gemini 2.5 Flash-Lite Preview (Thinking, 06-17) | 1,183.371 |
| 38 | Qwen3-VL-235B-A22B-Instruct | 1,181.4717 |
| 39 | GLM-5V-Turbo | 1,174.6155 |
| 40 | GPT-5.2 | 1,174.5587 |
| 41 | Gemma 3 27B IT | 1,169.9598 |
| 42 | Claude Sonnet 4.6 | 1,166.5968 |
| 43 | MiMo-V2.5 | 1,162.5257 |
| 44 | MiniMax-M3 | 1,160.8475 |
| 45 | Gemma 4 26B A4B | 1,157.6845 |
| 46 | Qwen3.5-27B | 1,149.2257 |
| 47 | Mistral Small 3.2 (2506) | 1,134.3547 |
| 48 | Mistral Small 3.1 24B Instruct (2503) | 1,130.5295 |
| 49 | Mistral Medium 3.1 (2508) | 1,128.4312 |
| 50 | Mistral Medium 3 (2505) | 1,125.3955 |