OpenCompass Code - Generation (CompassBench 2411): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 34 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O1 Mini (2024-09-12) | 56.4 |
| 2 | Claude 3.5 Sonnet (20241022) | 32.7 |
| 3 | GLM-4 Plus | 31.7 |
| 4 | GPT-4o (2024-11-20) | 30.7 |
| 5 | Mistral Large 2 (Nov) Instruct (2411) | 28.7 |
| 6 | Llama 3.1 405B Instruct FP8 | 27.7 |
| 7 | Qwen 2.5 72B Instruct | 26.7 |
| 8 | Grok Beta | 26.7 |
| 9 | 360gpt2-pro | 26.7 |
| 10 | DeepSeek V2.5 | 23.8 |
| 11 | TeleChat2 | 23.8 |
| 12 | GPT-4o (2024-08-06) | 22.8 |
| 13 | Yi Lightning | 20.8 |
| 14 | Step 2 16K | 18.8 |
| 15 | Gemma 2 27B (IT) | 17.8 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-code-generation-compassbench-2411 · How It Works · Data refreshed daily, snapshot 2026-09-19.