gpt3-finnish-13B: benchmark results
Provider: OpenAI. Access: API.
Aggregate Rating 1124 ± 16, rank #10454 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - TruthfulQA MC2 | 44.47 | Accuracy (%) | 48.7 |
| MMLU-by-task - Machine Learning | 31.25 | Accuracy (%) | 43.7 |
| MMLU-by-task - TruthfulQA MC1 | 25.7 | Accuracy (%) | 37.2 |
| MMLU-by-task - Human Aging | 34.98 | Accuracy (%) | 29.3 |
| MMLU-by-task - Marketing | 29.91 | Accuracy (%) | 28.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 44.47 | MC2 (%) (0-shot) | 27.3 |
| MMLU-by-task - Moral Scenarios | 24.25 | Accuracy (%) | 25.7 |
| MMLU-by-task - Virology | 30.12 | Accuracy (%) | 25.1 |
| MMLU-by-task - Business Ethics | 29 | Accuracy (%) | 24.5 |
| MMLU-by-task - Prehistory | 27.16 | Accuracy (%) | 23.3 |
| MMLU-by-task - Clinical Knowledge | 27.17 | Accuracy (%) | 22.1 |
| MMLU-by-task - Anatomy | 27.41 | Accuracy (%) | 21.8 |
Interactive version: theaggregate.ai/model?slug=gpt3-finnish-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.