MiniChat-1.5-3B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1362 ± 21, rank #2397 of 2928 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 50.71 | MC2 (%) (0-shot) | 49.3 |
| Open LLM Leaderboard v1 - GSM8K | 24.18 | Accuracy (%) (5-shot) | 43.4 |
| Open LLM Leaderboard v1 - MMLU | 46.67 | Accuracy (%) (5-shot) | 25.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 46.5 | Normalized accuracy (%) (25-shot) | 21.6 |
| Open LLM Leaderboard v1 - HellaSwag | 68.28 | Normalized accuracy (%) (10-shot) | 19.3 |
| Open LLM Leaderboard v1 - WinoGrande | 65.04 | Accuracy (%) (5-shot) | 18.2 |
| 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 |
| Open Portuguese LLM - ENEM | 0 | Accuracy (%) | 0.8 |
| Open Portuguese LLM - BLUEX | 0 | Accuracy (%) | 0.7 |
Interactive version: theaggregate.ai/model?slug=minichat-1-5-3b · How It Works · Data refreshed daily, snapshot 2026-09-23.