Vision · Style Control · English
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Claude Fable 5 (High) | 1,303.1828 |
| 2 | Claude Opus 4.7 (High) | 1,302.185 |
| 3 | Claude Opus 4.7 | 1,301.9235 |
| 4 | Claude Opus 4.6 (High) | 1,301.1808 |
| 5 | Claude Opus 4.6 | 1,295.2689 |
| 6 | Qwen3.8-Max | 1,294.111 |
| 7 | Gemini 3.8 Flash (High) | 1,291.5095 |
| 8 | Muse Spark | 1,290.0724 |
| 9 | GPT-6 Astra (Max) | 1,287.6062 |
| 10 | Gemini 3.7 Flash (High) | 1,287.3645 |
| 11 | Claude Opus 5.5 (High) | 1,284.4923 |
| 12 | GPT-5.6 Sol (xHigh) | 1,283.6515 |
| 13 | Claude Sonnet 4.6 | 1,282.7565 |
| 14 | Claude Opus 4.8 | 1,281.4264 |
| 15 | Claude Opus 5 (High) | 1,280.9846 |
| 16 | GPT-5.4 (High) | 1,280.9466 |
| 17 | GPT-5.5 | 1,280.9256 |
| 18 | GPT-5.2 Chat (20260210) | 1,280.4638 |
| 19 | GPT-5.5 (High) | 1,280.0533 |
| 20 | Claude Opus 4.8 (High) | 1,279.8959 |
| 21 | GPT-6.1 Sol (Max) | 1,279.3725 |
| 22 | Muse Spark 1.3 (Max) | 1,279.3185 |
| 23 | Claude Fable 5.1 (Max) | 1,279.273 |
| 24 | Gemini 3.5 Flash (High) | 1,278.1852 |
| 25 | GPT-5.5 Instant | 1,277.9253 |
| 26 | Dola Seed 2.0 Pro | 1,277.5211 |
| 27 | GPT-5.4 | 1,277.207 |
| 28 | Muse Spark 1.3 (xHigh) | 1,277.1503 |
| 29 | Muse Spark 1.1 | 1,276.0961 |
| 30 | Gemini 3.6 Flash (High) | 1,275.9712 |
| 31 | Muse Spark 1.2 (xHigh) | 1,275.1866 |
| 32 | Gemini 3.5 Flash (Medium) | 1,275.0942 |
| 33 | Gemini 3 Pro | 1,274.8545 |
| 34 | Grok 4.5 | 1,274.7441 |
| 35 | Gemini 3.1 Pro Preview | 1,272.3793 |
| 36 | Step 5 Preview | 1,271.4348 |
| 37 | GLM-5.3-Flash | 1,270.2128 |
| 38 | GPT-5.6 Terra (xHigh) | 1,269.0307 |
| 39 | DeepSeek-V4.1-Flash-20260910 (Max) | 1,268.1413 |
| 40 | Grok 4.6 (High) | 1,267.4834 |
| 41 | Kimi K2.6 | 1,267.3507 |
| 42 | Gemini 3.5 Flash-Lite | 1,267.3071 |
| 43 | Claude Sonnet 5.5 (xHigh) | 1,264.8147 |
| 44 | Qwen3.7-Plus | 1,263.7182 |
| 45 | Claude Sonnet 5 (High) | 1,263.0117 |
| 46 | Mistral Large 4 | 1,262.8652 |
| 47 | GPT-5.6 Luna (xHigh) | 1,262.2969 |
| 48 | Gemini 3 Flash | 1,261.9675 |
| 49 | Gemma 4 31B | 1,256.1581 |
| 50 | Grok 4.20 Beta (Reasoning, 0309) | 1,255.0572 |