Mistral-Starling-merge-trial3-7B: benchmark results
Provider: grimjim. Access: Open.
Aggregate Rating 1425 ± 33, rank #4911 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - ARC Challenge | 66.55 | Normalized accuracy (%) (25-shot) | 74 |
| Open LLM Leaderboard v1 - WinoGrande | 80.03 | Accuracy (%) (5-shot) | 72 |
| Open LLM Leaderboard v1 - HellaSwag | 84.81 | Normalized accuracy (%) (10-shot) | 68.9 |
| Open LLM Leaderboard v1 - MMLU | 64.18 | Accuracy (%) (5-shot) | 66.5 |
| Open LLM Leaderboard v1 - GSM8K | 52.99 | Accuracy (%) (5-shot) | 64.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 52.85 | MC2 (%) (0-shot) | 57.7 |
Interactive version: theaggregate.ai/model?slug=mistral-starling-merge-trial3-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.