List your company

Question Answering on CosmosQA (test)

86.23AccuracyExpert II (CosmosQA)
61.73868.096574.45580.8135May 14, 2026

Evaluation results

MethodLinks
Expert II (CosmosQA)Seed Model=LLaMA-3.1-8B2026.0586.23
MetaMoESeed Model=LLaMA-3.1-8B2026.0585.8
UnrestrictedMoESeed Model=LLaMA-3.1-8B2026.0585.7
ModelSoupSeed Model=LLaMA-3.1-8B2026.0584.25
FlexOlmoSeed Model=LLaMA-3.1-8B2026.0581.11
BTXSeed Model=LLaMA-3.1-8B2026.0581.04
BTMSeed Model=LLaMA-3.1-8B2026.0580.84
Expert II (CosmosQA)Seed Model=LLaMA-3.2-3B2026.0578.69
UnrestrictedMoESeed Model=LLaMA-3.2-3B2026.0578.39
Expert I (CSQA)Seed Model=LLaMA-3.1-8B2026.0577.29
Expert III (SocialIQA)Seed Model=LLaMA-3.1-8B2026.0576.98
MetaMoESeed Model=LLaMA-3.2-3B2026.0576.05
ZeroShotSeed Model=LLaMA-3.1-8B2026.0575.98
BTMSeed Model=LLaMA-3.2-3B2026.0575.44
ModelSoupSeed Model=LLaMA-3.2-3B2026.0575.24
FlexOlmoSeed Model=LLaMA-3.2-3B2026.0573.33
BTXSeed Model=LLaMA-3.2-3B2026.0572.06
Expert I (CSQA)Seed Model=LLaMA-3.2-3B2026.0570.18
Expert III (SocialIQA)Seed Model=LLaMA-3.2-3B2026.0568.04
ZeroShotSeed Model=LLaMA-3.2-3B2026.0562.68