OpenCompass LLM - Knowledge - English (CompassBench 2405): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 39 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mixtral 8x22B Instruct (v0.1) | 83.7 |
| 2 | Claude 3 Opus | 83.5 |
| 3 | Mistral Large | 82.9 |
| 4 | DBRX | 81.9 |
| 5 | Llama 3 70B Instruct | 81.7 |
| 6 | Command-R+ | 81.2 |
| 7 | GPT-4 Turbo | 80.9 |
| 8 | Yi Large | 80.1 |
| 9 | Qwen 1.5 110B Chat | 79.7 |
| 10 | DeepSeek V2 Chat | 79.4 |
| 11 | Qwen 1.5 72B Chat | 76.8 |
| 12 | Mixtral 8x7B Instruct (v0.1) | 76.5 |
| 13 | Moonshot v1 8K | 76 |
| 14 | GPT-4o (2024-05-13) | 75.4 |
| 15 | GLM-4 | 75 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-llm-knowledge-english-compassbench-2405 · How It Works · Data refreshed daily, snapshot 2026-09-19.