OPT-19M-ChatSalad: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1085 ± 41, rank #10854 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.36 | MC2 (%) (0-shot) | 51.8 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 24.4 | Normalized accuracy (%) (25-shot) | 3.6 |
| Open LLM Leaderboard v1 - WinoGrande | 49.72 | Accuracy (%) (5-shot) | 2.3 |
| Open LLM Leaderboard v1 - MMLU | 23.12 | Accuracy (%) (5-shot) | 1 |
| Open LLM Leaderboard v1 - HellaSwag | 25.15 | Normalized accuracy (%) (10-shot) | 0.9 |
Interactive version: theaggregate.ai/model?slug=opt-19m-chatsalad · How It Works · Data refreshed daily, snapshot 2026-11-08.