Competitive Programming on LiveCodeBench v5
82.8Scoreo4-mini
Evaluation results
| Method | Links | ||
|---|---|---|---|
| o4-miniEffort=high2025.12 | 82.8 | — | |
| Qwen3-235B-A22BMode=Thinking-25072025.12 | 81.6 | — | |
| o3Effort=high2025.12 | 78.1 | — | |
| Nemotron-Cascade-14B-ThinkingModel Size=14B, Mode=Thinking2025.12 | 77.5 | — | |
| o4-miniEffort=medium2025.12 | 76.3 | — | |
| Qwen3-Next-80B-A3B-Thinking2025.12 | 76 | — | |
| Magistral-Medium-1.2-25092025.12 | 75 | — | |
| DeepSeek-R1-05282025.12 | 74.8 | — | |
| Nemotron-Cascade-8B-ThinkingModel Size=8B, Mode=Thinking2025.12 | 74.5 | — | |
| Nemotron-Cascade-8BModel Size=8B2025.12 | 74.3 | — | |
| Gemini-2.5-Pro-06-052025.12 | 73.5 | — | |
| OpenReasoning-Nemotron-32B2025.12 | 71.8 | — | |
| Qwen3-235B-A22BMode=thinking mode2025.12 | 70.7 | — | |
| Llama-3.3-Nemotron-Super-49B-v1.52025.12 | 70.3 | — | |
| AReaL-Boba-2-14B2025.12 | 70.3 | — | |
| NVIDIA-Nemotron-Nano-9B-v22025.12 | 68.2 | — | |
| Klear-Reasoner-8B2025.12 | 66 | — | |
| X-Coder-7B2026.01 | 62.9 | -17.2 | |
| AceReason-Nemotron-1.0-14B2025.12 | 61.1 | — | |
| X-Coder-7B-SFTTraining Stage=SFT2026.01 | 60.3 | -17.9 | |
| Qwen3-8B2026.01 | 57.5 | -30.6 | |
| AceReason-Nemotron-1.1-7B2025.12 | 57.2 | — |