LiveCodeBench v6
OpenCompass · 48 models
| Rank | Model | Score |
|---|---|---|
| 1 | GLM-5 | 86.2 |
| 2 | Step-3.5-Flash | 83.9 |
| 3 | GLM-4.7 | 83.8 |
| 4 | GPT-5-2025-08-07 (high) | 83.2 |
| 5 | Qwen3.5-397B-A17B | 83 |
| 6 | Gemini-3-Pro-Preview | 82.9 |
| 7 | DeepSeek-V3.2-Speciale | 80.9 |
| 8 | GPT-5-mini-2025-08-07 (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-2025-08-07 (high) | 74 |
| 14 | MiniMax-M2 | 74 |
| 16 | MiniMax-M2.5 | 73.6 |
| 17 | o3-2025-04-16 | 72.7 |
| 18 | MiMo-V2-Flash | 71.8 |
| 19 | TeleChat-thinking | 71.7 |
| 20 | Gemini-2.5-Pro | 71.3 |
| 21 | o4-mini-2025-04-16 (high) | 71 |
| 22 | Qwen3-235B-A22B-Thinking-2507 | 70.6 |
| 23 | gpt-oss-20b (high) | 68.4 |
| 24 | Seed-OSS-36B-Instruct | 67.3 |
| 25 | Qwen3-Next-80B-A3B-Thinking | 66.3 |
| 26 | GLM-4.5 | 65 |
| 27 | JT-Think | 64.9 |
| 28 | doubao-seed-1.6-thinking-250615 | 61.8 |
| 29 | DeepSeek-R1-0528 | 61 |
| 30 | Qwen3-30B-A3B-Thinking-2507 | 59.4 |
| 31 | Qwen3-32B (Thinking) | 57.6 |
| 32 | Finix-P1-32B (Thinking) | 54.9 |
| 33 | Qwen3-Next-80B-A3B-Instruct | 54.8 |
| 34 | MiniCPM-SALA | 54.7 |
| 35 | Qwen3-4B-Thinking-2507 | 51.6 |
| 36 | Qwen3-8B (Thinking) | 50.1 |
| 37 | LongCat-Flash-Chat | 48.2 |
| 38 | Claude Sonnet 4 (Thinking) | 47.5 |
| 39 | ERNIE-4.5-21B-A3B-Thinking | 47 |
| 40 | Kimi-K2-Instruct | 46.8 |
| 41 | Hunyuan-A13B-Instruct | 43.9 |
| 42 | Qwen3-235B-A22B-Instruct-2507 | 43 |
| 43 | ERNIE-4.5-300B-A47B-PT | 41 |
| 44 | Qwen3-30B-A3B-Instruct-2507 | 38.7 |
| 45 | GPT-4.1-20250414 | 37.2 |
| 46 | Qwen3-4B-Instruct-2507 | 33.5 |
| 47 | Llama4-Maverick-17B-128E-Instruct | 33.2 |
| 48 | Gemma-3-27B-it | 30.8 |