opt-1.3B: benchmark results
Meta's OPT-1.3B, part of the Open Pretrained Transformer suite of decoder-only models from 125M to 175B parameters, designed to match GPT-3-class model sizes and performance. Provider: Meta. Released 2022-05-03. Access: Open.
Aggregate Rating 1134 ± 13, rank #1636 of 1656 rated models, from 95 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Physics | 31.37 | Accuracy (%) | 77.6 |
| MMLU-by-task - Global Facts | 33 | Accuracy (%) | 51.6 |
| ToolBench - WebShop Long | 0 | Task Score | 44.2 |
| MMLU-by-task - High School Physics | 28.48 | Accuracy (%) | 39.1 |
| MMLU-by-task - Abstract Algebra | 27 | Accuracy (%) | 34 |
| MMLU-by-task - Econometrics | 26.32 | Accuracy (%) | 32.9 |
| MMLU-by-task - Nutrition | 30.07 | Accuracy (%) | 31.4 |
| MMLU-by-task - High School Computer Science | 32 | Accuracy (%) | 31.3 |
| MMLU-by-task - Professional Medicine | 36.76 | Accuracy (%) | 29.5 |
| MMLU-by-task - Electrical Engineering | 28.28 | Accuracy (%) | 28.1 |
| MMLU-by-task - High School Statistics | 28.24 | Accuracy (%) | 27 |
| MMLU-by-task - Professional Psychology | 27.12 | Accuracy (%) | 26.3 |
Interactive version: theaggregate.ai/model?slug=opt-1-3b · How It Works · Data refreshed daily, snapshot 2026-10-20.