Text · Style Control · Legal & Government
Arena · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Gemini 4 Carbon (High) | 1,549.7535 |
| 2 | Gemini 4 Argon (High) | 1,523.6179 |
| 3 | Muse Spark 1.2 (xHigh) | 1,518.8311 |
| 4 | Muse Wonder (Max) | 1,513.2944 |
| 5 | Claude Opus 4.7 (High) | 1,510.7629 |
| 6 | Claude Fable 5 (High) | 1,510.3317 |
| 7 | Kimi K3 (Max) | 1,509.1666 |
| 8 | Claude Opus 4.6 (High) | 1,509.1207 |
| 9 | Claude Opus 4.6 | 1,506.9938 |
| 10 | GPT-6.1 Sol (Max) | 1,504.8174 |
| 11 | Claude Opus 5 (Max) | 1,502.4396 |
| 12 | Claude Opus 5 (High) | 1,501.5387 |
| 13 | Gemini 3 Pro | 1,501.3708 |
| 14 | Muse Spark | 1,499.7459 |
| 15 | Claude Opus 5.5 (High) | 1,499.7289 |
| 16 | Muse Spark 1.3 (Max) | 1,499.4129 |
| 17 | Gemini 3.1 Pro Preview | 1,498.1603 |
| 18 | Muse Spark 1.1 | 1,497.8615 |
| 19 | Claude Opus 4.8 | 1,497.7278 |
| 20 | Gemini 3.7 Flash (High) | 1,495.6052 |
| 21 | Claude Opus 4.7 | 1,495.5827 |
| 22 | GPT-5.5 (High) | 1,495.5198 |
| 23 | Claude Opus 4.8 (High) | 1,495.4414 |
| 24 | GPT-5.6 Sol (xHigh) | 1,495.2911 |
| 25 | GLM-5.2 (Max) | 1,492.4508 |
| 26 | Gemini 3.8 Flash (High) | 1,492.3226 |
| 27 | Claude Fable 5.1 (Max) | 1,491.5857 |
| 28 | GPT-5.4 (High) | 1,490.1061 |
| 29 | Qwen3.8-Max | 1,489.1245 |
| 30 | Claude Opus 4.5 (High, 32K, 20251101) | 1,487.1738 |
| 31 | Claude Sonnet 5.5 (xHigh) | 1,486.2172 |
| 32 | GPT-5.5 | 1,486.0319 |
| 33 | Claude Sonnet 4.6 | 1,484.2934 |
| 34 | GPT-6 Astra (Max) | 1,484.1597 |
| 35 | Gemini 3.5 Flash (Medium) | 1,483.6758 |
| 36 | Gemini 3 Flash | 1,483.2517 |
| 37 | Claude Opus 4.5 (20251101) | 1,482.8035 |
| 38 | DeepSeek-V4-Pro (High, 20260813) | 1,480.8753 |
| 39 | GPT-5.2 Chat (20260210) | 1,480.7547 |
| 40 | Gemini 3.6 Flash (High) | 1,480.389 |
| 41 | Qwen3.7-Max-Preview | 1,479.7874 |
| 42 | Gemini 3.5 Flash (High) | 1,478.6947 |
| 43 | Grok 4.20 Beta (Reasoning, 0309) | 1,478.2576 |
| 44 | Grok 4.5 | 1,477.3923 |
| 45 | GPT-5.5 Instant | 1,476.4346 |
| 46 | GPT-5.4 | 1,475.276 |
| 47 | Grok 4.1 (Thinking) | 1,475.0883 |
| 48 | MiMo-V2.5-Pro | 1,474.9859 |
| 49 | GPT-5.6 Terra (xHigh) | 1,474.877 |
| 50 | DeepSeek-V4-Pro | 1,474.4406 |