EXPERIMENT-SFT-m7b2-3-merged [4bit]: benchmark results
Provider: Other.
Aggregate Rating 1393 ± 33, rank #6431 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 78.45 | Accuracy (%) (5-shot) | 63.3 |
| Open LLM Leaderboard v1 - MMLU | 62.3 | Accuracy (%) (5-shot) | 54.9 |
| Open LLM Leaderboard v1 - HellaSwag | 82.39 | Normalized accuracy (%) (10-shot) | 50.9 |
| Open LLM Leaderboard v1 - GSM8K | 34.57 | Accuracy (%) (5-shot) | 50.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 59.56 | Normalized accuracy (%) (25-shot) | 43.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 40.04 | MC2 (%) (0-shot) | 12.8 |
Interactive version: theaggregate.ai/model?slug=experiment-sft-m7b2-3-merged-4bit · How It Works · Data refreshed daily, snapshot 2026-11-08.