List your company

Mathematical Reasoning on MATH (test) (Score)

42.68MATH ScorePAD
30.241633.470836.739.9292Feb 3, 2026

Evaluation results

MethodLinks
PADsource model=qwen3-32b, train dataset=gsm8k2026.0242.68
PADsource model=qwen3-8b, train dataset=gsm8k2026.0242.53
PADsource model=gemma3-27b-it, train dataset=gsm8k2026.0242.17
DAsource model=qwen3-32b, train dataset=gsm8k2026.0241.55
RSFTsource model=qwen3-8b, train dataset=gsm8k2026.0241.39
DAsource model=qwen3-8b, train dataset=gsm8k2026.0241.17
DAsource model=gemma3-27b-it, train dataset=gsm8k2026.0240.94
RSFTsource model=gemma3-27b-it, train dataset=gsm8k2026.0240.79
RSFTsource model=qwen3-32b, train dataset=gsm8k2026.0238.74
DAsource model=qwen3-32b, train dataset=medmcqa2026.0234.54
DAsource model=gemma3-27b-it, train dataset=medmcqa2026.0233.23
PADsource model=gemma3-27b-it, train dataset=medmcqa2026.0232.92
RSFTsource model=qwen3-32b, train dataset=medmcqa2026.0232.66
PADsource model=qwen3-32b, train dataset=medmcqa2026.0232.58
PADsource model=qwen3-8b, train dataset=medmcqa2026.0232.27
RSFTsource model=gemma3-27b-it, train dataset=medmcqa2026.0232.01
RSFTsource model=qwen3-8b, train dataset=medmcqa2026.0231.7
DAsource model=qwen3-8b, train dataset=medmcqa2026.0230.72