tinyllama-chat: benchmark results
Provider: Singapore Univ. Access: Open.
Aggregate Rating 1156 ± 35, rank #9877 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 2.27 | Accuracy (%) (5-shot) | 19.8 |
| Open LLM Leaderboard v1 - HellaSwag | 61.11 | Normalized accuracy (%) (10-shot) | 15.1 |
| Open LLM Leaderboard v1 - WinoGrande | 61.17 | Accuracy (%) (5-shot) | 14.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 36.01 | Normalized accuracy (%) (25-shot) | 13.5 |
| Open LLM Leaderboard v1 - MMLU | 25.43 | Accuracy (%) (5-shot) | 8.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 37.47 | MC2 (%) (0-shot) | 6 |
Interactive version: theaggregate.ai/model?slug=tinyllama-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.