List your company

Science Question Answering on GPQA (Accuracy, Avg Acc, Avg TPF)

56.94AccuracyPhi-4-14B
26.613634.486842.3650.2332Jul 7, 2026

Evaluation results

MethodLinks
Phi-4-14BScale=14B, Gen. Mode=AR2026.0756.9460.821
Nemotron-Labs-Diffusion-14BScale=14B, Gen. Mode=AR2026.0754.5567.461
Ministral3-14B-Instruct-2512Scale=14B, Gen. Mode=AR2026.0752.0262.971
Nemotron-Labs-Diffusion-14BScale=14B, Gen. Mode=Quad. SS2026.0752.0268.156.92
Qwen3-14BScale=14B, Gen. Mode=AR2026.0750.5165.171
Nemotron-Labs-Diffusion-14BScale=14B, Gen. Mode=Diff.2026.0748.9966.512.74
Nemotron-Labs-Diffusion-14BScale=14B, Gen. Mode=Linear SS2026.0747.4766.365.96
Nemotron-Labs-Diffusion-3BScale=3B, Gen. Mode=Quad. SS2026.0742.9355.85.42
Phi-4-mini-InstructScale=3B, Gen. Mode=AR2026.0740.9149.21
Nemotron-Labs-Diffusion-3BScale=3B, Gen. Mode=AR2026.0739.3955.51
Gemma-3-12B-ITScale=14B, Gen. Mode=AR2026.0738.3258.031
Phi-3-Medium-14BScale=14B, Gen. Mode=AR2026.0737.5649.341
Qwen3-4BScale=3B, Gen. Mode=AR2026.0737.1853.231
Nemotron-Labs-Diffusion-3BScale=3B, Gen. Mode=Linear SS2026.0735.86554.36
Nemotron-Labs-Diffusion-3BScale=3B, Gen. Mode=Diff.2026.0733.8452.91.91
Ministral3-3B-Instruct-2512Scale=3B, Gen. Mode=AR2026.0728.7947.971
Llama-3.2-3B-InstructScale=3B, Gen. Mode=AR2026.0727.7839.91