Vision · Style Control · Captioning
Arena · 34 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro Preview | 1,281.6156 |
| 2 | Gemini 3 Pro | 1,276.5851 |
| 3 | GPT-5.2 (High) | 1,262.1194 |
| 4 | Gemini 2.5 Pro | 1,250.5864 |
| 5 | GPT-5.1 (High) | 1,248.237 |
| 6 | Gemma 4 26B A4B | 1,238.9268 |
| 7 | Gemini 3 Flash | 1,233.7928 |
| 8 | Gemini 3.1 Flash-Lite Preview | 1,225.4807 |
| 9 | ChatGPT-4o Latest (20250326) | 1,212.7463 |
| 10 | Gemini 2.5 Flash | 1,211.3501 |
| 11 | Qwen3-VL-235B-A22B-Instruct | 1,211.0336 |
| 12 | GPT-4.1 (2025-04-14) | 1,209.9203 |
| 13 | Gemini 3 Flash (Minimal) | 1,209.0135 |
| 14 | Kimi K2.5 (Thinking) | 1,197.9607 |
| 15 | GPT-5 (High) | 1,196.0498 |
| 16 | GPT-5 Chat | 1,194.2233 |
| 17 | GPT-4.1 mini (2025-04-14) | 1,193.2599 |
| 18 | o4-mini (2025-04-16) | 1,184.8136 |
| 19 | o3 (2025-04-16) | 1,182.5713 |
| 20 | Gemini 2.5 Flash-Lite Preview (Thinking, 06-17) | 1,182.4442 |
| 21 | GLM-5V-Turbo | 1,179.7555 |
| 22 | GPT-5 mini (High) | 1,175.1711 |
| 23 | Qwen3.5-397B-A17B | 1,174.4849 |
| 24 | GPT-5.2 | 1,171.8627 |
| 25 | Grok 4 (0709) | 1,170.472 |
| 26 | Gemma 4 31B | 1,170.0801 |
| 27 | GPT-5.1 | 1,162.6467 |
| 28 | Gemini 2.0 Flash (001) | 1,149.8662 |
| 29 | Mistral Small 3.1 24B Instruct (2503) | 1,133.0815 |
| 30 | Mistral Medium 3.1 (2508) | 1,129.551 |
| 31 | Gemma 3 27B IT | 1,116.7484 |
| 32 | Qwen3.5-27B | 1,095.4517 |
| 33 | Mistral Medium 3 (2505) | 1,090.0444 |
| 34 | Mistral Small 3.2 (2506) | 1,050.491 |