Llama 2 22B Blocktriangular [float16] [rev: 40a51343ae77]: benchmark results
Provider: chargoddard. Access: Open.
Aggregate Rating 1350 ± 35, rank #7709 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 82.59 | Normalized accuracy (%) (10-shot) | 52.6 |
| Open LLM Leaderboard v1 - WinoGrande | 76.32 | Accuracy (%) (5-shot) | 47.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 58.53 | Normalized accuracy (%) (25-shot) | 40.1 |
| Open LLM Leaderboard v1 - MMLU | 54.64 | Accuracy (%) (5-shot) | 34.4 |
| Open LLM Leaderboard v1 - GSM8K | 9.78 | Accuracy (%) (5-shot) | 30.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 39.3 | MC2 (%) (0-shot) | 10.7 |
Interactive version: theaggregate.ai/model?slug=llama-2-22b-blocktriangular-float16-rev-40a51343ae77 · How It Works · Data refreshed daily, snapshot 2026-11-08.