TinyLlama-MoE-Chat [bfloat16] [rev: 2d786c9077b9]: benchmark results
Provider: Singapore Univ.
Aggregate Rating 1168 ± 34, rank #9783 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 29.71 | Accuracy (%) (5-shot) | 16.4 |
| Open LLM Leaderboard v1 - WinoGrande | 62.19 | Accuracy (%) (5-shot) | 15.3 |
| Open LLM Leaderboard v1 - GSM8K | 0.99 | Accuracy (%) (5-shot) | 15 |
| Open LLM Leaderboard v1 - HellaSwag | 59.29 | Normalized accuracy (%) (10-shot) | 13.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 34.73 | Normalized accuracy (%) (25-shot) | 12.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 39.35 | MC2 (%) (0-shot) | 10.8 |
Interactive version: theaggregate.ai/model?slug=tinyllama-moe-chat-bfloat16-rev-2d786c9077b9 · How It Works · Data refreshed daily, snapshot 2026-11-08.