mpt-7B-8k-instruct [float16] [rev: 736f68aceeb6]: benchmark results
Provider: Databricks.
Aggregate Rating 1267 ± 34, rank #9098 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 20.7 | Accuracy (%) (5-shot) | 41.5 |
| Open LLM Leaderboard v1 - HellaSwag | 74.47 | Normalized accuracy (%) (10-shot) | 24.7 |
| Open LLM Leaderboard v1 - MMLU | 41.97 | Accuracy (%) (5-shot) | 21.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 45.9 | Normalized accuracy (%) (25-shot) | 21.1 |
| Open LLM Leaderboard v1 - WinoGrande | 65.98 | Accuracy (%) (5-shot) | 19.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 35.21 | MC2 (%) (0-shot) | 2.1 |
Interactive version: theaggregate.ai/model?slug=mpt-7b-8k-instruct-float16-rev-736f68aceeb6 · How It Works · Data refreshed daily, snapshot 2026-11-08.