trinity-large-preview: benchmark results
Arcee AI's Trinity Large preview, a ~400B model (January 2026). Provider: Arcee AI. Released 2026-01-27. Access: Open.
Unified ELO 1526 ± 1, rank #564 of 1392 rated models, from 100 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AGC-Bench - fann_or_flop | 2.3 | Dataset z-score | 98.8 |
| AGC-Bench - science_analogies | 1.94 | Dataset z-score | 93.8 |
| UGI Leaderboard | 52.11 | UGI Score | 93.3 |
| AGC-Bench - ocw_connections | 1.08 | Dataset z-score | 90.9 |
| AGC-Bench - futuregen | 1.2 | Dataset z-score | 90 |
| UGI - Natural Intelligence | 41.34 | NatInt Score | 87.2 |
| AGC-Bench - story_generation_rocstories | 0.89 | Dataset z-score | 86.6 |
| CringeBench | 0.76 | Cringe Score (0-10, lower is better) | 80.3 |
| AGC-Bench - hypobench | 0.35 | Dataset z-score | 79.3 |
| AGC-Bench - pun_eval | 0.67 | Dataset z-score | 79.3 |
| UGI - Writing | 40.72 | Writing Score | 75.5 |
| Vectara Hallucination Leaderboard | 93.1 | Factual Consistency Rate (%) | 72.6 |
Interactive version: theaggregate.ai/model?slug=trinity-large-preview · How It Works · Data refreshed daily, snapshot 2026-09-05.