List your company

Math on AMC23 (Score %)

78.3ScoreMPO+
11.94829.17446.463.626Apr 17, 2026Apr 24, 2026May 2, 2026May 9, 2026May 17, 2026May 24, 2026Jun 1, 2026

Evaluation results

MethodLinks
MPO+Backbone=olmo-3.1-32b-it-sft2026.0478.3
Soft+Backbone=olmo-3.1-32b-it-sft2026.0477.5
Pair+Backbone=olmo-3.1-32b-it-sft2026.0477.2
Mag+Backbone=olmo-3.1-32b-it-sft2026.0476.6
MPO+Backbone=olmo-3-7b-it-sft2026.0473.1
Soft+Backbone=olmo-3-7b-it-sft2026.0472.8
Pair+Backbone=olmo-3-7b-it-sft2026.0469.5
RFTBackbone=olmo-3.1-32b-it-sft2026.0468
Mag+Backbone=olmo-3-7b-it-sft2026.0467.8
DPOBackbone=olmo-3.1-32b-it-sft2026.0467.7
DPOBackbone=olmo-3-7b-it-sft2026.0461.6
TSV-MergeModel Category=Merged Models2026.0655.5
TAModel Category=Merged Models2026.0655
RESMERGEModel Category=Merged Models2026.0655
RFTBackbone=olmo-3-7b-it-sft2026.0454.7
TIESModel Category=Merged Models2026.0652.75
RAMModel Category=Merged Models2026.0652.75
DARE + TIESModel Category=Merged Models2026.0652.5
ISO-CModel Category=Merged Models2026.0652.5
BaseBackbone=olmo-3.1-32b-it-sft2026.0452.3
AMPOModel Category=Base and Expert Models2026.0651.67
ToolRLModel Category=Base and Expert Models2026.0649.75
Qwen2.5-7B-InstructModel Category=Base and Expert Models2026.0649.5
ISO-CTSModel Category=Merged Models2026.0647.5
BaseBackbone=olmo-3-7b-it-sft2026.0442
MemoryAgentModel Category=Base and Expert Models2026.0622.25
Mag+Backbone=gemma-3-4b-sft2026.0416.7
MPO+Backbone=gemma-3-4b-sft2026.0416.6
DPOBackbone=gemma-3-4b-sft2026.0416.2
Pair+Backbone=gemma-3-4b-sft2026.0415.6
BaseBackbone=gemma-3-4b-sft2026.0415
RFTBackbone=gemma-3-4b-sft2026.0414.7
Soft+Backbone=gemma-3-4b-sft2026.0414.5