List your company
ResearchFormerly WizWand

Programming Reasoning on LiveCodeBench v5

66pass@1Klear-Reasoner-8B
33.03241.59150.1558.709Aug 11, 2025Sep 8, 2025Oct 7, 2025Nov 4, 2025Dec 3, 2025Dec 31, 2025Jan 29, 2026
Updated 7mo ago

Evaluation results

MethodLinks
Klear-Reasoner-8BMaximum Inference Length=64K2025.0866
OpenReasoning-Nemotron-7BMaximum Inference Length=64K2025.0865.6
InfLLM-v2Model Size=14B, Temperature=0.6, Max output length=32k, Training context length=32k, Training tokens=1.2T, Sampling strategy=pass@12026.0164.2
SPLAModel Size=14B, Temperature=0.6, Max output length=32k, Training context length=32k, Training tokens=1.2T, Sampling strategy=pass@12026.0162.4
SPAModel Size=14B, Temperature=0.6, Max output length=32k, Training context length=32k, Training tokens=1.2T, Sampling strategy=pass@12026.0162
Dense AttentionModel Size=14B, Temperature=0.6, Max output length=32k, Training context length=32k, Training tokens=1.2T, Sampling strategy=pass@12026.0161.6
Klear-Reasoner-8BMaximum Inference Length=32K2025.0861.6
Deepseek-R1-0528-Distill-8BMaximum Inference Length=64K2025.0861
POLARIS-4B-PreviewMaximum Inference Length=96K2025.0858.5
Klear-Reasoner-8B-SFTMaximum Inference Length=32K2025.0858.5
MiMo-7B-RLMaximum Inference Length=32K2025.0857.8
Qwen3-8BMaximum Inference Length=32K2025.0857.5
AceReason-Nemotron-1.1-7BMaximum Inference Length=32K2025.0857.2
NSAModel Size=14B, Temperature=0.6, Max output length=32k, Training context length=32k, Training tokens=1.2T, Sampling strategy=pass@12026.0149.1
Skywork-OR1-7BMaximum Inference Length=32K2025.0847.6
AReal-boba-RL-7BMaximum Inference Length=32K2025.0834.3