OpenCompass Language - Dialogue - English (CompassBench 2409): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 30 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-4 Plus | 61.8 |
| 2 | Step 2 16K | 58.5 |
| 3 | DeepSeek V2.5 | 54.5 |
| 4 | GPT-4o (2024-05-13) | 49.5 |
| 5 | GPT-4o Mini (2024-07-18) | 48.9 |
| 6 | GLM-4 9B Chat | 48.6 |
| 7 | Yi-1.5-9B Chat | 47.7 |
| 8 | Mistral Nemo Instruct (2407) | 47.7 |
| 9 | Llama 3.1 70B Instruct | 47.3 |
| 10 | Qwen 2.5 72B Instruct | 47 |
| 11 | Yi Large | 46.6 |
| 12 | Llama 3.1 405B Instruct FP8 | 45.9 |
| 13 | GPT-4o (2024-08-06) | 43.6 |
| 14 | Mistral-Small-Instruct-2409 | 42.3 |
| 15 | Mistral Large 2 (Jul) | 41.8 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-language-dialogue-english-compassbench-2409 · How It Works · Data refreshed daily, snapshot 2026-09-19.