Tinyllama-Cinder-1.3B-Reason-Test: benchmark results
Provider: Josephgflowers. Access: Open.
Aggregate Rating 1163 ± 36, rank #9805 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 4.85 | Accuracy (%) (5-shot) | 23.4 |
| Open LLM Leaderboard v1 - WinoGrande | 63.93 | Accuracy (%) (5-shot) | 16.7 |
| Open LLM Leaderboard v1 - HellaSwag | 58.24 | Normalized accuracy (%) (10-shot) | 13.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 34.56 | Normalized accuracy (%) (25-shot) | 12.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 39.93 | MC2 (%) (0-shot) | 12.4 |
| Open LLM Leaderboard v1 - MMLU | 25.79 | Accuracy (%) (5-shot) | 9.8 |
Interactive version: theaggregate.ai/model?slug=tinyllama-cinder-1-3b-reason-test · How It Works · Data refreshed daily, snapshot 2026-11-08.