TinyLlama-MoE-Chat [float16] [rev: 2d786c9077b9]: benchmark results
Provider: Singapore Univ.
Aggregate Rating 1170 ± 33, rank #9770 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 29.9 | Accuracy (%) (5-shot) | 16.5 |
| Open LLM Leaderboard v1 - GSM8K | 1.21 | Accuracy (%) (5-shot) | 16 |
| Open LLM Leaderboard v1 - WinoGrande | 62.51 | Accuracy (%) (5-shot) | 15.5 |
| Open LLM Leaderboard v1 - HellaSwag | 59.22 | Normalized accuracy (%) (10-shot) | 13.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 34.64 | Normalized accuracy (%) (25-shot) | 12.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 39.37 | MC2 (%) (0-shot) | 10.8 |
Interactive version: theaggregate.ai/model?slug=tinyllama-moe-chat-float16-rev-2d786c9077b9 · How It Works · Data refreshed daily, snapshot 2026-11-08.