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 |
|---|---|
| Claude Opus 5 | 1561 |
| Opus 4.6 | 1526 |
| Claude Fable 5 | 1512 |
| Gemini 3.5 Flash | 1512 |
| Opus 4.7 | 1505 |
| Gemini 3.6 Flash | 1504 |
| GPT-5.4 | 1495 |
| Opus 4.8 | 1493 |
| GPT-5.6 Sol | 1492 |
| MiMo-V2.5-Pro | 1492 |
| GPT-5.5 | 1490 |
| ERNIE 5.1 | 1487 |
| Muse Spark 1.1 | 1485 |
| GLM-5.2 | 1484 |
| Sonnet 4.6 | 1482 |
| Grok 4.5 | 1481 |
| Gemini 3.1 Pro Preview | 1479 |
| Kimi K2.6 | 1479 |
| Qwen3.7-Plus | 1477 |
| Sonnet 5 | 1477 |
| GLM-5.1 | 1476 |
| Gemini 3 Pro Preview | 1475 |
| Kimi K2.5 | 1474 |
| GPT-5.6 Terra | 1470 |
| Opus 4.5 | 1470 |
| Gemma 4 26B A4B | 1470 |
| Qwen3.7 Max Preview | 1470 |
| Gemini 3 Flash Preview | 1465 |
| Gemma 4 31B | 1465 |
| MiMo-V2-Pro | 1463 |
| GPT-5.6 Luna | 1460 |
| Inkling | 1458 |
| Qwen3.5 397B A17B | 1458 |
| Gemini 2.5 Pro | 1454 |
| DeepSeek-V4-Pro | 1454 |
| Muse Spark | 1454 |
| MiniMax M3 | 1451 |
| MiMo-V2.5 | 1450 |
| Qwen3.6 Plus (2026-04-02) | 1449 |
| GLM-5 | 1449 |