OpenCompass LLM - Code (CompassBench 2404): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 51 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o (2024-05-13) | 74.1 |
| 2 | GPT-4 Turbo | 73.7 |
| 3 | DeepSeek V2 Chat | 67.3 |
| 4 | GPT-4 Turbo (Preview) | 67.2 |
| 5 | Claude 3 Opus | 66 |
| 6 | GPT-3.5 Turbo | 60.7 |
| 7 | Moonshot v1 8K | 60.6 |
| 8 | Qwen 1.5 110B Chat | 58 |
| 9 | Llama 3 70B Instruct | 54.7 |
| 10 | internlm2-chat-20B | 54.2 |
| 11 | GLM-4 | 54 |
| 12 | Qwen 1.5 72B Chat | 52 |
| 13 | Mistral Large | 50.4 |
| 14 | DBRX | 50.1 |
| 15 | Qwen-72B-Chat | 49.3 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-llm-code-compassbench-2404 · How It Works · Data refreshed daily, snapshot 2026-09-19.