OpenCompass Code - LCBench - English (CompassBench 2407): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 36 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet (20240620) | 81.2 |
| 2 | DeepSeek V2 Chat (0628) | 74.4 |
| 3 | GPT-4o Mini (2024-07-18) | 67.4 |
| 4 | GPT-4o (2024-05-13) | 67.3 |
| 5 | Mistral Large | 63.8 |
| 6 | Gemma 2 27B (IT) | 60.7 |
| 7 | GLM-4 (0520) | 52.4 |
| 8 | Yi Large | 51.7 |
| 9 | Llama 3.1 70B Instruct | 51.3 |
| 10 | Mistral Large 2 (Jul) | 50.5 |
| 11 | Qwen 1.5 110B Chat | 46.6 |
| 12 | Qwen 2 72B Instruct | 42.7 |
| 13 | Yi 1.5 34B Chat | 40 |
| 14 | Gemma 2 9B (IT) | 39.4 |
| 15 | GLM-4 9B Chat | 38.3 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-code-lcbench-english-compassbench-2407 · How It Works · Data refreshed daily, snapshot 2026-09-19.