EXPERIMENT-SFT-m7b2-1-merged [4bit]: benchmark results
Provider: Other.
Aggregate Rating 1360 ± 32, rank #7429 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 76.64 | Accuracy (%) (5-shot) | 49.6 |
| Open LLM Leaderboard v1 - GSM8K | 25.32 | Accuracy (%) (5-shot) | 44 |
| Open LLM Leaderboard v1 - MMLU | 56.76 | Accuracy (%) (5-shot) | 39.8 |
| Open LLM Leaderboard v1 - HellaSwag | 79.75 | Normalized accuracy (%) (10-shot) | 39 |
| Open LLM Leaderboard v1 - ARC Challenge | 56.83 | Normalized accuracy (%) (25-shot) | 36.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.29 | MC2 (%) (0-shot) | 34 |
Interactive version: theaggregate.ai/model?slug=experiment-sft-m7b2-1-merged-4bit · How It Works · Data refreshed daily, snapshot 2026-11-08.