dolphin-2.9.2-Phi-3-Medium: benchmark results
Provider: Cognitive Computations. Released 2024-05-31. Access: Open.
Aggregate Rating 1395 ± 17, rank #1240 of 1656 rated models, from 29 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - ASSIN2 RTE | 93.59 | Macro F1 (%) | 90.5 |
| Open LLM Leaderboard - BBH | 64.57 | Score | 90 |
| Open LLM Leaderboard - MMLU-Pro | 45.55 | Score | 84.6 |
| Open Chinese LLM - GSM8K | 57.92 | Accuracy (%) | 80.5 |
| Open LLM Leaderboard - GPQA | 32.72 | Score | 79.2 |
| Open Portuguese LLM - BLUEX | 60.78 | Accuracy (%) | 79.2 |
| Open Portuguese LLM - FaQuAD NLI | 76.71 | Macro F1 (%) | 77.2 |
| Open Portuguese LLM - OAB Exams | 50.3 | Accuracy (%) | 76.6 |
| Open Portuguese LLM - ENEM | 70.05 | Accuracy (%) | 74.9 |
| Open Chinese LLM - C-Eval Semantic | 78.97 | Accuracy (%) | 68.3 |
| Open LLM Leaderboard - MATH Level 5 | 18.28 | Score | 68 |
| Open Chinese LLM - CMMLU | 58.76 | Accuracy (%) | 66.6 |
Interactive version: theaggregate.ai/model?slug=dolphin-2-9-2-phi-3-medium · How It Works · Data refreshed daily, snapshot 2026-10-20.