trinity-v1 (Publisher: jan-hq): benchmark results
Provider: Arcee AI.
Aggregate Rating 1460 ± 39, rank #3309 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 71.65 | Accuracy (%) (5-shot) | 96.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 72.27 | Normalized accuracy (%) (25-shot) | 91.4 |
| Open LLM Leaderboard v1 - HellaSwag | 88.36 | Normalized accuracy (%) (10-shot) | 91.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 69.31 | MC2 (%) (0-shot) | 88.8 |
| Open LLM Leaderboard v1 - MMLU | 65.2 | Accuracy (%) (5-shot) | 82.9 |
| Open LLM Leaderboard v1 - WinoGrande | 82 | Accuracy (%) (5-shot) | 81.7 |
Interactive version: theaggregate.ai/model?slug=trinity-v1-publisher-jan-hq · How It Works · Data refreshed daily, snapshot 2026-11-08.