List your company
ResearchFormerly WizWand

Scientific Question Answering on GPQA Diamond (pass@1)

65.2pass@1Qwen3
3.73619.69335.6551.607May 13, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Qwen3Model Category=Original Models, Sampling Temperature=0.6, Shuffle options=true2026.0565.2
Qwen3-8192Model Category=Original Models, Max Generation Length=8192, Sampling Temperature=0.6, Shuffle options=true2026.0549
LUFFYModel Category=Off-Policy and Mixed-Policy, Sampling Temperature=0.6, Shuffle options=true2026.0538.9
TGPOModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.0537.9
TGPO-annealingModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.0537.4
KDRLModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.0535.4
TGPORModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.0533.3
GRPO++Model Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.0532.3
Oat-ZeroModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.0523.7
SimpleRL-ZeroModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.0523.2
SFTModel Category=Off-Policy and Mixed-Policy, Sampling Temperature=0.6, Shuffle options=true2026.0520.2
PRIME-ZeroModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.0518.2
Qwen2.5-Math-7BModel Category=Original Models, Sampling Temperature=0.6, Shuffle options=true2026.0511.1
OP DistillModel Category=On-Policy Methods, Sampling Temperature=0.6, Shuffle options=true2026.056.1