microsoft/Phi-3.5-MoE-instruct
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| MATH | math | 88.7 | Math | medium | | Math | GSM8K (8-shot, CoT) | 88.7 | 84.2 | 82.4 | 84.9 | 82.4 | 91.3 | |
| MMLU | knowledge | 69.9 | Multilingual MMLU | medium | | Multilingual MMLU | 69.9 | 58.9 | 56.2 | 63.8 | 77.2 | 72.9 | |
| TydiQA | knowledge | 67.1 | MEGA TyDi QA | medium | | MEGA TyDi QA | 67.1 | 63.7 | 54.5 | 65.6 | 63.6 | 81.8 | |
| MGSM | math | 58.7 | MGSM | medium | | MGSM | 58.7 | 63.3 | 56.7 | 75.1 | 75.8 | 81.7 | |
| MMLU-Pro | knowledge | 45.3 | Multilingual MMLU-Pro | medium | | Multilingual MMLU-Pro | 45.3 | 34.0 | 21.4 | 43.0 | 57.9 | 53.2 | |
none scraped.