Arena Text — Occupational Mathematical (No Style Control)
Math
Raw Arena rating for mathematical industry prompts without style-control adjustment. Higher ratings indicate stronger preference in blind pairwise user votes.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 4 Argon | 1549 |
| Claude Opus 5 | 1543 |
| Claude Fable 5.1 | 1543 |
| Opus 4.6 | 1525 |
| Claude Opus 5.5 | 1525 |
| Gemini 3.8 Flash | 1520 |
| Claude Fable 5 | 1515 |
| GPT-6.1 Sol | 1514 |
| MiMo-V2.6-Pro | 1511 |
| Claude Sonnet 5.5 | 1511 |
| Muse Wonder | 1511 |
| Opus 4.7 | 1509 |
| Kimi K3 | 1504 |
| Gemini 3.7 Flash | 1502 |
| GLM-5.3 | 1498 |
| GPT-5.4 | 1497 |
| Opus 4.8 | 1497 |
| GLM-5.3 Flash | 1497 |
| GPT-5.5 | 1496 |
| GPT-5.6 Sol | 1495 |
| Gemini 3.5 Flash | 1494 |
| Muse Spark 1.3 | 1493 |
| Gemini 3.6 Flash | 1492 |
| Qwen3.8-Max | 1491 |
| ERNIE 5.1 | 1491 |
| MiMo-V2.5-Pro | 1491 |
| GLM-5.2 | 1490 |
| Muse Spark 1.1 | 1485 |
| DeepSeek V4.1 Flash | 1484 |
| Hy3 | 1483 |
| Sonnet 4.6 | 1483 |
| GPT-6 Astra | 1482 |
| Sonnet 5 | 1482 |
| Grok 4.5 | 1482 |
| Muse Spark 1.2 | 1481 |
| Kimi K2.6 | 1480 |
| Gemini 3.1 Pro Preview | 1478 |
| MiMo-V2.6-Flash | 1478 |
| GPT-5.6 Terra | 1478 |
| Gemma 4 26B A4B IT | 1476 |