Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Competitive Programming on LiveCodeBench 2408 - 2505 v6
Loading...
80.2
Score
o4-mini
54.2
60.95
67.7
74.45
Dec 15, 2025
Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Score
o4-mini
Effort=high
2025.12
80.2
Qwen3-235B-A22B
Mode=Thinking-2507
2025.12
78.7
o3
Effort=high
2025.12
75.8
Nemotron-Cascade-14B-Thinking
Model Size=14B, Mode=T...
2025.12
74.6
o4-mini
Effort=medium
2025.12
74.2
Gemini-2.5-Pro-06-05
2025.12
73.6
DeepSeek-R1-0528
2025.12
73.3
Qwen3-Next-80B-A3B-Thinking
2025.12
73.2
Nemotron-Cascade-8B-Thinking
Model Size=8B, Mode=Th...
2025.12
71.4
Nemotron-Cascade-8B
Model Size=8B
2025.12
71.1
OpenReasoning-Nemotron-32B
2025.12
70.2
Llama-3.3-Nemotron-Super-49B-v1.5
2025.12
68.1
AReaL-Boba-2-14B
2025.12
67.4
Qwen3-235B-A22B
Mode=thinking mode
2025.12
67.3
NVIDIA-Nemotron-Nano-9B-v2
2025.12
65.3
Meta-CWM-32B
2025.12
63.5
Klear-Reasoner-8B
2025.12
63
AceReason-Nemotron-1.0-14B
2025.12
58.7
AceReason-Nemotron-1.1-7B
2025.12
55.2
Feedback
Search any
task
Search any
task