List your company

Scientific Reasoning on GPQA Diamond (accuracy (avg@32))

58.13Accuracy (avg@32)PPPO
26.961235.053143.14551.2369Dec 17, 2025

Evaluation results

MethodLinks
PPPOBackbone=Qwen3-8B, Evaluation Protocol=zero-shot, avg@322025.1258.13
DAPOBackbone=Qwen3-8B, Evaluation Protocol=zero-shot, avg@322025.1255.18
DAPO-FTBackbone=Qwen3-8B, Evaluation Protocol=zero-shot, avg@322025.1254.77
PPPOBackbone=Qwen3-4B, Evaluation Protocol=zero-shot, avg@322025.1252.07
GRPOBackbone=Qwen3-8B, Evaluation Protocol=zero-shot, avg@322025.1250.51
DAPOBackbone=Qwen3-4B, Evaluation Protocol=zero-shot, avg@322025.1249.37
INTUITORBackbone=Qwen3-8B, Evaluation Protocol=zero-shot, avg@322025.1249.31
DAPO-FTBackbone=Qwen3-4B, Evaluation Protocol=zero-shot, avg@322025.1249.21
GRPOBackbone=Qwen3-4B, Evaluation Protocol=zero-shot, avg@322025.1246.78
INTUITORBackbone=Qwen3-4B, Evaluation Protocol=zero-shot, avg@322025.1246.43
Qwen3-8BBackbone=Qwen3-8B, Evaluation Protocol=zero-shot, avg@322025.1246.12
Qwen3-4BBackbone=Qwen3-4B, Evaluation Protocol=zero-shot, avg@322025.1243.59
PPPOBackbone=Qwen3-1.7B, Evaluation Protocol=zero-shot, avg@322025.1239.52
DAPOBackbone=Qwen3-1.7B, Evaluation Protocol=zero-shot, avg@322025.1231.82
DAPO-FTBackbone=Qwen3-1.7B, Evaluation Protocol=zero-shot, avg@322025.1231.44
INTUITORBackbone=Qwen3-1.7B, Evaluation Protocol=zero-shot, avg@322025.1229.96
GRPOBackbone=Qwen3-1.7B, Evaluation Protocol=zero-shot, avg@322025.1229.8
Qwen3-1.7BBackbone=Qwen3-1.7B, Evaluation Protocol=zero-shot, avg@322025.1228.16