OpenCompass Agent - T-Eval - English (CompassBench 2405): leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 39 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o (2024-05-13) | 88.1 |
| 2 | GPT-4 Turbo | 86.6 |
| 3 | Mistral Large | 86.2 |
| 4 | Mixtral 8x22B Instruct (v0.1) | 86.2 |
| 5 | Claude 3 Opus | 85.9 |
| 6 | DeepSeek V2 Chat | 85.2 |
| 7 | Yi Large | 85.1 |
| 8 | Command-R+ | 83.1 |
| 9 | Yi 1.5 34B Chat | 81.4 |
| 10 | Moonshot v1 8K | 81.2 |
| 11 | GLM-4 | 80.7 |
| 12 | Qwen 1.5 32B Chat | 79.3 |
| 13 | GPT-3.5 Turbo | 78.4 |
| 14 | Yi-1.5-9B Chat | 77.6 |
| 15 | Mistral 7B Instruct (v0.3) | 77.4 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-agent-t-eval-english-compassbench-2405 · How It Works · Data refreshed daily, snapshot 2026-09-19.