mpt-7B: benchmark results
Provider: Databricks. Released 2023-05-05. Access: Open.
Unified ELO 1287 ± 1, rank #1360 of 1392 rated models, from 30 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HellaSwag | 76.4 | Accuracy (%) | 45.4 |
| PIQA | 80.6 | Accuracy (%) | 45 |
| OpenBookQA | 51.4 | Accuracy (%) | 35.7 |
| BoolQ | 75 | Accuracy (%) | 32.5 |
| WinoGrande | 68.6 | Accuracy (%) | 32.5 |
| ARC Challenge (AI2) | 42.6 | Accuracy (%) | 27.6 |
| Epoch AI - Lambada | 70 | Score | 16 |
| Big-Bench Hard | 35.6 | Average (%) | 14.6 |
| LLM Benchmarker Suite | 41.96 | Average Score (%) | 14.3 |
| Open LLM Leaderboard - IFEval | 21.52 | Score | 14.1 |
| Open LLM Leaderboard - MuSR | 2.9 | Score | 13.5 |
| Open LLM Leaderboard - BBH | 6.55 | Score | 13.4 |
Interactive version: theaggregate.ai/model?slug=mpt-7b · How It Works · Data refreshed daily, snapshot 2026-09-05.