Arena Text — Legal & Government (No Style Control)
Professional Work
Raw Arena rating for legal and government industry prompts without style-control adjustment. Higher ratings indicate stronger preference in blind pairwise user votes.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5 | 1544 |
| Kimi K3 | 1532 |
| Opus 4.6 | 1512 |
| Opus 4.7 | 1502 |
| Claude Fable 5 | 1495 |
| Gemini 3.6 Flash | 1494 |
| Gemini 3 Pro Preview | 1494 |
| GPT-5.5 | 1490 |
| Muse Spark | 1490 |
| Gemini 3.1 Pro Preview | 1487 |
| GPT-5.4 | 1486 |
| Gemini 3.5 Flash | 1485 |
| Muse Spark 1.1 | 1482 |
| GPT-5.6 Terra | 1479 |
| Gemini 2.5 Pro | 1478 |
| MiMo-V2.5-Pro | 1478 |
| Gemini 3 Flash Preview | 1477 |
| Opus 4.8 | 1475 |
| Qwen3.7 Max Preview | 1473 |
| GLM-5.2 | 1472 |
| GLM-5.1 | 1471 |
| Sonnet 4.6 | 1469 |
| ERNIE 5.1 | 1469 |
| GPT-5.6 Sol | 1467 |
| DeepSeek-V4-Pro | 1462 |
| Sonnet 5 | 1460 |
| Grok 4.5 | 1459 |
| Opus 4.5 | 1458 |
| Kimi K2.6 | 1458 |
| Qwen3.7-Plus | 1458 |
| Gemma 4 26B A4B | 1457 |
| DeepSeek-V3.1-Terminus | 1457 |
| GPT-5.1 | 1455 |
| GPT-5.6 Luna | 1453 |
| GLM-5 | 1452 |
| GLM 4.6 | 1450 |
| Sonnet 4.5 | 1449 |
| MiMo-V2-Pro | 1447 |
| GLM-4.7 | 1445 |
| Grok 4.1 | 1444 |