MiniChat-3B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1229 ± 26, rank #9432 of 10916 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 45.67 | MC2 (%) (0-shot) | 31.8 |
| Open LLM Leaderboard v1 - GSM8K | 10.54 | Accuracy (%) (5-shot) | 31.5 |
| Open LLM Leaderboard v1 - MMLU | 39.17 | Accuracy (%) (5-shot) | 20.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 44.03 | Normalized accuracy (%) (25-shot) | 19.8 |
| Open LLM Leaderboard v1 - WinoGrande | 65.27 | Accuracy (%) (5-shot) | 18.4 |
| Open LLM Leaderboard v1 - HellaSwag | 67.19 | Normalized accuracy (%) (10-shot) | 18.3 |
| AlpacaEval 1.0 | 48.82 | Win Rate (%) | 11.9 |
| AlpacaEval | 31.96 | Length-Controlled Win Rate (%) | 10.5 |
| AlpacaEval 2.0 | 5.73 | LC Win Rate (%) | 7.2 |
| Open Portuguese LLM - FaQuAD NLI | 0 | Macro F1 (%) | 1 |
| Open Portuguese LLM - ASSIN2 RTE | 0 | Macro F1 (%) | 0.9 |
| Open Portuguese LLM - OAB Exams | 0 | Accuracy (%) | 0.9 |
Interactive version: theaggregate.ai/model?slug=minichat-3b · How It Works · Data refreshed daily, snapshot 2026-11-08.