OpenCompass Language - Dialogue — leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 26 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 Max (2026-01-23) | 98.9 |
| 2 | Claude Sonnet 4.5 (Thinking) | 98.8 |
| 3 | Kimi K2.5 | 98.6 |
| 4 | Kimi K2 (Thinking) | 98.5 |
| 5 | Qwen 3 235B A22B (Thinking) | 98.1 |
| 6 | Claude Opus 4.5 (Thinking) | 98.1 |
| 7 | GPT-OSS-120B (High) | 98 |
| 8 | Ring-1T | 98 |
| 9 | MiniMax-M2.1 | 97 |
| 10 | Ling-1T | 96.3 |
| 11 | Grok 4.1 | 96.2 |
| 12 | O3 (2025-04-16) (High) | 96.1 |
| 13 | Qwen 3 Next 80B A3B (Thinking) | 95.5 |
| 14 | Seed-OSS-36B-Instruct | 94.4 |
| 15 | ERNIE 5.0 | 94.1 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-language-dialogue · How the rankings work · Data refreshed daily, snapshot 2026-07-22.