Ministral-3-8B-Instruct: benchmark results
Provider: Mistral.
Aggregate Rating 1569 ± 41, rank #1299 of 10489 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| WuYuEval - Expert Module - Elo | 1818.82 | Elo rating from pairwise judged comparisons | 87.5 |
| NormGym - Joint Success (Seen Layout) | 3.3 | Joint Task & Norm-Compliance Success Rate (%), Seen Layout | 50 |
| NormGym - Joint Success (Unseen Layouts) | 4 | Joint Task & Norm-Compliance Success Rate (%), Unseen Layout | 50 |
| NormGym - Task Success (Seen Layout) | 49.7 | Task Goal Completion Score (%), Seen Layout | 50 |
| NormGym - Task Success (Unseen Layouts) | 50 | Task Goal Completion Score (%), Unseen Layouts | 50 |
| WuYuEval - Foundation Module - Accuracy | 79.74 | Accuracy (%) | 46.9 |
| WuYuEval - Foundation Module - Macro-F1 | 82.91 | Macro-F1 (%) | 43.8 |
| WuYuEval - Expert Module - Judge Score | 0.75 | Mean anchor-calibrated LLM-as-a-judge score (0-1) | 37.5 |
Interactive version: theaggregate.ai/model?slug=ministral-3-8b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-20.