OpenCompass LLM - Code - English (CompassBench 2407): leaderboard

Metric: Score (%). Source: rank.opencompass.org.cn. 36 models tracked.

Top models

#ModelScore
1Claude 3.5 Sonnet (20240620)71
2GPT-4o (2024-05-13)68.9
3Mistral Large65.7
4DeepSeek V2 Chat (0628)65.5
5GPT-4o Mini (2024-07-18)64.7
6Mistral Large 2 (Jul)57.8
7Gemma 2 27B (IT)57
8Llama 3.1 70B Instruct56.9
9GLM-4 (0520)56.8
10Yi Large54.6
11Qwen 2 72B Instruct50.7
12Qwen 1.5 110B Chat50.3
13GLM-4 9B Chat47.6
14Moonshot v1 8K46.8
15Yi 1.5 34B Chat46.6

Interactive version: theaggregate.ai/benchmark?slug=opencompass-llm-code-english-compassbench-2407 · How It Works · Data refreshed daily, snapshot 2026-09-19.