List your company

Science Question Answering on GPQA Diamond (avg@1)

61.62Avg@1 ScoreSTAR-1-mix
43.232848.006452.7857.5536Feb 14, 2026Feb 15, 2026Feb 16, 2026Feb 17, 2026Feb 18, 2026Feb 19, 2026

Evaluation results

MethodLinks
STAR-1-mixModel=Qwen3-14B, Setting=STAR-1-mix2026.0261.62
AgentModel=Qwen3-14B, Setting=Agent2026.0260.61
AgentModel=Qwen3-8B, Setting=Agent2026.0259.6
IFPOModel=Qwen3-14B, Setting=IFPO2026.0258.59
STAR-1Model=Qwen3-14B, Setting=STAR-12026.0258.08
BCModel=Qwen3-14B, Setting=BC2026.0256.57
BCModel=Qwen3-8B, Setting=BC2026.0254.55
IFPOModel=Qwen3-8B, Setting=IFPO2026.0253.03
IFPOModel=Qwen3-4B, Setting=IFPO2026.0252.53
STAR-1-mixModel=Qwen3-4B, Setting=STAR-1-mix2026.0252.02
BCModel=Qwen3-4B, Setting=BC2026.0251.52
STAR-1-mixModel=Qwen3-8B, Setting=STAR-1-mix2026.0251.52
AgentModel=Qwen3-4B, Setting=Agent2026.0250.51
STAR-1Model=Qwen3-4B, Setting=STAR-12026.0249.49
SafeChainModel=Qwen3-14B, Setting=SafeChain2026.0249.49
SafeChainModel=Qwen3-8B, Setting=SafeChain2026.0247.98
STAR-1Model=Qwen3-8B, Setting=STAR-12026.0247.47
SafeChainModel=Qwen3-4B, Setting=SafeChain2026.0244.44
Trinity Large Baseshot=5-shot2026.0243.94