llama-class-shishya-7B-ep3: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1274 ± 40, rank #9029 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 77.04 | Normalized accuracy (%) (10-shot) | 30 |
| Open LLM Leaderboard v1 - MMLU | 46.74 | Accuracy (%) (5-shot) | 25.4 |
| Open LLM Leaderboard v1 - WinoGrande | 70.8 | Accuracy (%) (5-shot) | 25.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 40.78 | Normalized accuracy (%) (25-shot) | 17.1 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 27.94 | MC2 (%) (0-shot) | 0 |
Interactive version: theaggregate.ai/model?slug=llama-class-shishya-7b-ep3 · How It Works · Data refreshed daily, snapshot 2026-11-08.