OpenCompass Math - Arithmetic (CompassBench 2411): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 34 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O1 Mini (2024-09-12) | 96 |
| 2 | Yi Lightning | 88 |
| 3 | DeepSeek V2.5 | 87.3 |
| 4 | Grok Beta | 86.7 |
| 5 | GPT-4o (2024-11-20) | 86 |
| 6 | 360gpt2-pro | 85.7 |
| 7 | GPT-4o (2024-08-06) | 84.7 |
| 8 | Mistral Large 2 (Nov) Instruct (2411) | 82 |
| 9 | TeleChat2 | 81.3 |
| 10 | GLM-4 Plus | 81 |
| 11 | Claude 3.5 Sonnet (20241022) | 79 |
| 12 | Qwen 2.5 72B Instruct | 78 |
| 13 | Llama 3.1 405B Instruct FP8 | 74 |
| 14 | Step 2 16K | 73 |
| 15 | Mistral-Small-Instruct-2409 | 71.3 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-math-arithmetic-compassbench-2411 · How It Works · Data refreshed daily, snapshot 2026-09-19.