List your company

Reasoning on AGIEval English

74.4Score (%)Pair+
47.98454.84261.768.558Apr 17, 2026

Evaluation results

MethodLinks
Pair+Backbone=olmo-3.1-32b-it-sft2026.0474.4
Soft+Backbone=olmo-3.1-32b-it-sft2026.0474.4
MPO+Backbone=olmo-3.1-32b-it-sft2026.0474.3
DPOBackbone=olmo-3.1-32b-it-sft2026.0473.6
Mag+Backbone=olmo-3.1-32b-it-sft2026.0472.6
RFTBackbone=olmo-3.1-32b-it-sft2026.0469
BaseBackbone=olmo-3.1-32b-it-sft2026.0467.7
Pair+Backbone=olmo-3-7b-it-sft2026.0461.8
Soft+Backbone=olmo-3-7b-it-sft2026.0461.4
MPO+Backbone=olmo-3-7b-it-sft2026.0460.9
Mag+Backbone=olmo-3-7b-it-sft2026.0459.4
DPOBackbone=olmo-3-7b-it-sft2026.0458.8
RFTBackbone=olmo-3-7b-it-sft2026.0455.8
BaseBackbone=olmo-3-7b-it-sft2026.0454.1
MPO+Backbone=gemma-3-4b-sft2026.0451.2
Pair+Backbone=gemma-3-4b-sft2026.0451.2
Soft+Backbone=gemma-3-4b-sft2026.0451.2
Mag+Backbone=gemma-3-4b-sft2026.0450.5
DPOBackbone=gemma-3-4b-sft2026.0450.3
BaseBackbone=gemma-3-4b-sft2026.0449.4
RFTBackbone=gemma-3-4b-sft2026.0449