List your company

Math on OlympiadBench (Score, TPF)

77.59ScoreQwen3-30B-A3B-Inst-2507
6.880425.237743.59561.9523Feb 9, 2026Feb 20, 2026Mar 3, 2026Mar 14, 2026Mar 25, 2026Apr 5, 2026Apr 17, 2026

Evaluation results

MethodLinks
Qwen3-30B-A3B-Inst-25072026.0277.59100
LLaDA2.1-flashInference Mode=Q Mode2026.0276.59381
Ling-flash-2.02026.0276.19100
LLaDA2.1-flashInference Mode=S Mode2026.0275.85646
LLaDA2.0-flash2026.0274.07370
Ling-mini-2.02026.0272.3—
LLaDA2.0-mini2026.0267.72.63
Pair+Backbone=olmo-3.1-32b-it-sft2026.0467—
LLaDA2.1-minimode=Q Mode2026.0266.673.99
MPO+Backbone=olmo-3.1-32b-it-sft2026.0464.7—
LLaDA2.1-minimode=S Mode2026.0264.37.08
Soft+Backbone=olmo-3.1-32b-it-sft2026.0464.1—
Mag+Backbone=olmo-3.1-32b-it-sft2026.0461.3—
DPOBackbone=olmo-3.1-32b-it-sft2026.0459.9—
MPO+Backbone=olmo-3-7b-it-sft2026.0457.3—
Pair+Backbone=olmo-3-7b-it-sft2026.0457.3—
Soft+Backbone=olmo-3-7b-it-sft2026.0457.3—
Mag+Backbone=olmo-3-7b-it-sft2026.0456—
Qwen3-8Bno think=true2026.0255.33—
RFTBackbone=olmo-3.1-32b-it-sft2026.0452.9—
DPOBackbone=olmo-3-7b-it-sft2026.0451.4—
RFTBackbone=olmo-3-7b-it-sft2026.0443.7—
BaseBackbone=olmo-3.1-32b-it-sft2026.0443.7—
BaseBackbone=olmo-3-7b-it-sft2026.0434.5—
Pair+Backbone=gemma-3-4b-sft2026.0413.5—
MPO+Backbone=gemma-3-4b-sft2026.0413.2—
Mag+Backbone=gemma-3-4b-sft2026.0411.9—
RFTBackbone=gemma-3-4b-sft2026.0411—
DPOBackbone=gemma-3-4b-sft2026.0410.8—
Soft+Backbone=gemma-3-4b-sft2026.0410.8—
BaseBackbone=gemma-3-4b-sft2026.049.6—