List your company

Scientific Question Answering on GPQA (Domain Scores)

65.8Biology Domain ScoreSkywork
31.58440.46749.3558.233May 26, 2026

Evaluation results

MethodLinks
SkyworkBase Model=Qwen3-8B-Base, Metric=Mean@N2026.0565.852.941.949
DAPO++Base Model=Qwen3-8B-Base, Metric=Mean@N2026.0565.86841.755.4
OpenR1Base Model=Qwen3-8B-Base, Metric=Mean@N2026.0561.839.840.942.4
Qwen3-8B-BaseModel Size=8B, Metric=Mean@N2026.0560.545.937.943.6
DeepMathBase Model=Qwen3-8B-Base, Metric=Mean@N2026.0560.558.733.347
DeepScaleRBase Model=Qwen3-8B-Base, Metric=Mean@N2026.0556.647.133.941.8
DAPOBase Model=Qwen3-8B-Base, Metric=Mean@N2026.0551.368.940.954
DeepMathBase Model=Qwen3-1.7B-Base, Metric=Mean@N2026.0548.739.242.541.7
DAPOBase Model=Qwen3-1.7B-Base, Metric=Mean@N2026.0544.733.135.835.5
DeepScaleRBase Model=Qwen3-1.7B-Base, Metric=Mean@N2026.0543.429.734.133.1
DAPO++Base Model=Qwen3-1.7B-Base, Metric=Mean@N2026.0542.13436.335.9
SkyworkBase Model=Qwen3-1.7B-Base, Metric=Mean@N2026.0536.835.238.236.7
OpenR1Base Model=Qwen3-1.7B-Base, Metric=Mean@N2026.0534.227.333.931.1
Qwen3-1.7B-BaseModel Size=1.7B, Metric=Mean@N2026.0532.928.530.129.7