OpenCompass LLM - Instruction Following (CompassBench 2501): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 40 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek R1 | 74 |
| 2 | GPT-4o (2024-11-20) | 67 |
| 3 | Gemini 2.0 Pro (Preview 02-05) | 64.8 |
| 4 | Yi Lightning | 64 |
| 5 | MiniMax-Text-01 | 63.2 |
| 6 | GLM-4 Plus | 62.9 |
| 7 | Gemini 2.0 Flash (001) | 62.5 |
| 8 | DeepSeek V3 | 58 |
| 9 | GPT-4o Mini (2024-07-18) | 53.5 |
| 10 | Qwen 2.5 Max | 52.7 |
| 11 | Mistral Large 2 (Nov) Instruct (2411) | 52.4 |
| 12 | Qwen 2.5 72B Instruct | 48.8 |
| 13 | Yi 1.5 34B Chat | 48.3 |
| 14 | Claude 3.5 Sonnet (20241022) | 48.2 |
| 15 | QwQ 32B-Preview | 43.5 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-llm-instruction-following-compassbench-2501 · How It Works · Data refreshed daily, snapshot 2026-09-19.