List your company

General Benchmark Aggregation on Overall Evaluation Suite

59.8Math AverageMPO+
17.88828.76939.6550.531Apr 17, 2026

Evaluation results

MethodLinks
MPO+Backbone=olmo-3.1-32b-it-sft2026.0459.858.258.8
Pair+Backbone=olmo-3.1-32b-it-sft2026.0459.659.559.6
Soft+Backbone=olmo-3.1-32b-it-sft2026.0458.558.358.4
Mag+Backbone=olmo-3.1-32b-it-sft2026.0457.757.357.5
DPOBackbone=olmo-3.1-32b-it-sft2026.0452.85956.5
Soft+Backbone=olmo-3-7b-it-sft2026.0452.649.750.9
Pair+Backbone=olmo-3-7b-it-sft2026.0452.251.852
MPO+Backbone=olmo-3-7b-it-sft2026.045251.651.7
Mag+Backbone=olmo-3-7b-it-sft2026.0451.151.351.2
RFTBackbone=olmo-3.1-32b-it-sft2026.0450.253.652.2
DPOBackbone=olmo-3-7b-it-sft2026.0446.549.848.5
RFTBackbone=olmo-3-7b-it-sft2026.0440.444.242.7
BaseBackbone=olmo-3.1-32b-it-sft2026.043952.947.3
BaseBackbone=olmo-3-7b-it-sft2026.043243.739
Pair+Backbone=gemma-3-4b-sft2026.0422.33631.8
MPO+Backbone=gemma-3-4b-sft2026.0421.936.932.3
Soft+Backbone=gemma-3-4b-sft2026.0421.737.832.8
Mag+Backbone=gemma-3-4b-sft2026.0421.636.632
DPOBackbone=gemma-3-4b-sft2026.0421.437.832.8
RFTBackbone=gemma-3-4b-sft2026.0420.234.129.8
BaseBackbone=gemma-3-4b-sft2026.0419.531.627.9