OpenCompass Research - LiveCodeBench v6 — leaderboard
Metric: Score (%). Source: rank.opencompass.org.cn. 48 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5 | 86.2 |
| 2 | Step 3.5 Flash | 83.9 |
| 3 | GLM-4.7 | 83.8 |
| 4 | GPT-5 (High) | 83.2 |
| 5 | Qwen 3.5 397B A17B | 83 |
| 6 | Gemini 3 Pro (Preview) | 82.9 |
| 7 | DeepSeek V3.2 Speciale | 80.9 |
| 8 | GPT-5 Mini (High) | 80.8 |
| 9 | Kimi K2.5 | 80.6 |
| 10 | GPT-OSS-120B (High) | 78.4 |
| 11 | GLM-4.6 | 78.2 |
| 12 | Kimi K2 (Thinking) | 77.1 |
| 13 | DeepSeek V3.2 | 75.4 |
| 14 | GPT-5 Nano (High) | 74 |
| 15 | MiniMax-M2 | 74 |
Interactive version: theaggregate.ai/benchmark?slug=opencompass-research-livecodebench-v6 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.