Question Answering on CosmosQA (test)
86.23AccuracyExpert II (CosmosQA)
Evaluation Results
| Method | Links | |
|---|---|---|
| Expert II (CosmosQA)Seed Model=LLaMA-3.1-8B2026.05 | 86.23 | |
| MetaMoESeed Model=LLaMA-3.1-8B2026.05 | 85.8 | |
| UnrestrictedMoESeed Model=LLaMA-3.1-8B2026.05 | 85.7 | |
| ModelSoupSeed Model=LLaMA-3.1-8B2026.05 | 84.25 | |
| FlexOlmoSeed Model=LLaMA-3.1-8B2026.05 | 81.11 | |
| BTXSeed Model=LLaMA-3.1-8B2026.05 | 81.04 | |
| BTMSeed Model=LLaMA-3.1-8B2026.05 | 80.84 | |
| Expert II (CosmosQA)Seed Model=LLaMA-3.2-3B2026.05 | 78.69 | |
| UnrestrictedMoESeed Model=LLaMA-3.2-3B2026.05 | 78.39 | |
| Expert I (CSQA)Seed Model=LLaMA-3.1-8B2026.05 | 77.29 | |
| Expert III (SocialIQA)Seed Model=LLaMA-3.1-8B2026.05 | 76.98 | |
| MetaMoESeed Model=LLaMA-3.2-3B2026.05 | 76.05 | |
| ZeroShotSeed Model=LLaMA-3.1-8B2026.05 | 75.98 | |
| BTMSeed Model=LLaMA-3.2-3B2026.05 | 75.44 | |
| ModelSoupSeed Model=LLaMA-3.2-3B2026.05 | 75.24 | |
| FlexOlmoSeed Model=LLaMA-3.2-3B2026.05 | 73.33 | |
| BTXSeed Model=LLaMA-3.2-3B2026.05 | 72.06 | |
| Expert I (CSQA)Seed Model=LLaMA-3.2-3B2026.05 | 70.18 | |
| Expert III (SocialIQA)Seed Model=LLaMA-3.2-3B2026.05 | 68.04 | |
| ZeroShotSeed Model=LLaMA-3.2-3B2026.05 | 62.68 |