Competitive Programming on LiveCodeBench 2408 - 2505 v6
80.2Scoreo4-mini
Evaluation results
| Method | Links | |
|---|---|---|
| o4-miniEffort=high2025.12 | 80.2 | |
| Qwen3-235B-A22BMode=Thinking-25072025.12 | 78.7 | |
| o3Effort=high2025.12 | 75.8 | |
| Nemotron-Cascade-14B-ThinkingModel Size=14B, Mode=Thinking2025.12 | 74.6 | |
| o4-miniEffort=medium2025.12 | 74.2 | |
| Gemini-2.5-Pro-06-052025.12 | 73.6 | |
| DeepSeek-R1-05282025.12 | 73.3 | |
| Qwen3-Next-80B-A3B-Thinking2025.12 | 73.2 | |
| Nemotron-Cascade-8B-ThinkingModel Size=8B, Mode=Thinking2025.12 | 71.4 | |
| Nemotron-Cascade-8BModel Size=8B2025.12 | 71.1 | |
| OpenReasoning-Nemotron-32B2025.12 | 70.2 | |
| Llama-3.3-Nemotron-Super-49B-v1.52025.12 | 68.1 | |
| AReaL-Boba-2-14B2025.12 | 67.4 | |
| Qwen3-235B-A22BMode=thinking mode2025.12 | 67.3 | |
| NVIDIA-Nemotron-Nano-9B-v22025.12 | 65.3 | |
| Meta-CWM-32B2025.12 | 63.5 | |
| Klear-Reasoner-8B2025.12 | 63 | |
| AceReason-Nemotron-1.0-14B2025.12 | 58.7 | |
| AceReason-Nemotron-1.1-7B2025.12 | 55.2 |