Coding on LiveCodeBench v6
92.5Pass@1DS-v4-Pro
Evaluation results
| Method | Links | |
|---|---|---|
| DS-v4-ProParameter Count=1.6T-A49B2026.06 | 92.5 | |
| DS-v4-FlashParameter Count=284B-A13B2026.06 | 90.9 | |
| Kimi-K2.6Parameter Count=1T-A32B2026.06 | 90.2 | |
| K-EXAONE-236B-A23BReasoning=On2026.03 | 89 | |
| Nemotron 3 UltraParameter Count=550B-A55B2026.06 | 89 | |
| Gemini 3-Pro2026.02 | 86.34 | |
| GLM-5.1Parameter Count=744B-A40B2026.06 | 85.7 | |
| GPT-5 (High)2026.02 | 81.7 | |
| DS V3.2-Thinking2026.02 | 81.06 | |
| Qwen-3.5Parameter Count=397B-17B2026.06 | 79.3 | |
| Qwen-3-30B-A3BReasoning=On2026.03 | 78.96 | |
| MiniMax-2.7Parameter Count=230B-A10B2026.06 | 77.2 | |
| ERNIE 5.02026.02 | 76.21 | |
| Mi:dm K 2.5 Pro (March ‘26)Reasoning=On2026.03 | 74.79 | |
| Gemini 2.5-Pro2026.02 | 72.9 | |
| Solar-Open-100BReasoning=On2026.03 | 72.8 | |
| HyperCLOVAX-SEED-Think-32BReasoning=On2026.03 | 68.34 | |
| Qwen-3-30B-A3BReasoning=Off2026.03 | 58.3 | |
| K-EXAONE-236B-A23BReasoning=Off2026.03 | 57.1 | |
| Mi:dm K 2.5 Pro (March ‘26)Reasoning=Off2026.03 | 40.1 | |
| HyperCLOVAX-SEED-Think-32BReasoning=Off2026.03 | 28.1 | |
| Youtu-LLMSize=2B, Type=Base, Prompt Setting=3-shot2025.12 | 9.7 | |
| Qwen3Size=4B, Type=Base, Prompt Setting=3-shot2025.12 | 6.9 | |
| Qwen3Size=1.7B, Type=Base, Prompt Setting=3-shot2025.12 | 5.1 | |
| Llama3.1Size=8B, Type=Base, Prompt Setting=3-shot2025.12 | 3.4 | |
| SmolLM3Size=3B, Type=Base, Prompt Setting=3-shot2025.12 | 2.9 | |
| Gemma3Size=4B, Type=Base, Prompt Setting=3-shot2025.12 | 2.9 |