OpenCompass LLM - Instruction Following - English (CompassBench 2501): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 40 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o (2024-11-20) | 68.8 |
| 2 | MiniMax-Text-01 | 67.3 |
| 3 | DeepSeek R1 | 62.7 |
| 4 | Gemini 2.0 Pro (Preview 02-05) | 57.3 |
| 5 | Yi Lightning | 57.3 |
| 6 | GLM-4 Plus | 57.1 |
| 7 | Mistral Large 2 (Nov) Instruct (2411) | 56 |
| 8 | DeepSeek V3 | 55 |
| 9 | GPT-4o Mini (2024-07-18) | 53.3 |
| 10 | Llama 3.1 70B Instruct | 51.7 |
| 11 | Gemini 2.0 Flash (001) | 50.4 |
| 12 | Qwen 2.5 Max | 48.3 |
| 13 | QwQ 32B-Preview | 46.7 |
| 14 | Llama 3.1 405B Instruct FP8 | 46 |
| 15 | Yi 1.5 34B Chat | 45.8 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-llm-instruction-following-english-compassbench-2501 · How It Works · Data refreshed daily, snapshot 2026-09-19.