OpenCompass Math - Arithmetic (CompassBench 2409): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 30 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 72B Instruct | 88.3 |
| 2 | Claude 3.5 Sonnet (20240620) | 86 |
| 3 | GPT-4o (2024-08-06) | 85.3 |
| 4 | GPT-4o (2024-05-13) | 84.7 |
| 5 | DeepSeek V2.5 | 82.7 |
| 6 | Qwen 2.5 7B Instruct | 79.7 |
| 7 | Mistral Large 2 (Jul) | 79.3 |
| 8 | Gemini 1.5 Pro | 78.3 |
| 9 | Llama 3.1 405B Instruct FP8 | 76.7 |
| 10 | GPT-4o Mini (2024-07-18) | 76.3 |
| 11 | GLM-4 Plus | 76 |
| 12 | Llama 3.1 70B Instruct | 74 |
| 13 | Mistral-Small-Instruct-2409 | 72.3 |
| 14 | Step 2 16K | 72.3 |
| 15 | Gemma 2 27B (IT) | 71 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-math-arithmetic-compassbench-2409 · How It Works · Data refreshed daily, snapshot 2026-09-19.