List your company

Mathematical Reasoning on Minerva 272

42.53Accuracy (Minerva 272)HAPO
17.25823.81930.3836.941Sep 20, 2025

Evaluation results

MethodLinks
HAPOBackbone=Qwen3-14B2025.0942.53
DAPO w/ Forking TokensBackbone=Qwen3-14B2025.0940.84
ArcherBackbone=Qwen3-14B2025.0940.62
Entropy EnvBackbone=Qwen3-14B2025.0940.56
EDGE-GRPOBackbone=Qwen3-14B2025.0940.31
Vanilla DAPOBackbone=Qwen3-14B2025.0939.97
Vanilla GRPOBackbone=Qwen3-14B2025.0937.52
HAPOBackbone=Qwen3-8B2025.0934.74
EDGE-GRPOBackbone=Qwen3-8B2025.0933.91
HAPOBackbone=Qwen2.5-Math-7B2025.0933.73
ArcherBackbone=Qwen3-8B2025.0933.22
Entropy EnvBackbone=Qwen3-8B2025.0932.95
DAPO w/ Forking TokensBackbone=Qwen2.5-Math-7B2025.0932.79
Vanilla DAPOBackbone=Qwen3-8B2025.0932.13
ArcherBackbone=Qwen2.5-Math-7B2025.0931.61
Entropy EnvBackbone=Qwen2.5-Math-7B2025.0931.43
Vanilla DAPOBackbone=Qwen2.5-Math-7B2025.0931.28
Vanilla GRPOBackbone=Qwen3-8B2025.0930.47
DAPO w/ Forking TokensBackbone=Qwen3-8B2025.0929.91
Vanilla GRPOBackbone=Qwen2.5-Math-7B2025.0929.85
EDGE-GRPOBackbone=Qwen2.5-Math-7B2025.0929.24
HAPOBackbone=Qwen2.5-Math-1.5B2025.0921.91
EDGE-GRPOBackbone=Qwen2.5-Math-1.5B2025.0919.93
Entropy EnvBackbone=Qwen2.5-Math-1.5B2025.0919.67
Vanilla DAPOBackbone=Qwen2.5-Math-1.5B2025.0919.52
ArcherBackbone=Qwen2.5-Math-1.5B2025.0919.14
DAPO w/ Forking TokensBackbone=Qwen2.5-Math-1.5B2025.0918.74
Vanilla GRPOBackbone=Qwen2.5-Math-1.5B2025.0918.23