TarsDolly: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1357 ± 35, rank #7518 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 81.85 | Normalized accuracy (%) (10-shot) | 47.3 |
| Open LLM Leaderboard v1 - WinoGrande | 76.24 | Accuracy (%) (5-shot) | 47 |
| Open LLM Leaderboard v1 - ARC Challenge | 59.3 | Normalized accuracy (%) (25-shot) | 42.8 |
| Open LLM Leaderboard v1 - MMLU | 56.26 | Accuracy (%) (5-shot) | 38.7 |
| Open LLM Leaderboard v1 - GSM8K | 10.16 | Accuracy (%) (5-shot) | 31.1 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 42.29 | MC2 (%) (0-shot) | 20.1 |
Interactive version: theaggregate.ai/model?slug=tarsdolly · How It Works · Data refreshed daily, snapshot 2026-11-08.