gpt-sw3-356m-instruct — benchmark results
Provider: AI Sweden. Released 2023-04-28. Access: Open.
Unified ELO 1051 ± 37, rank #1768 of 1776 rated models, from 94 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Icelandic NLU - NQII | 33.29 | Reading comprehension Score (%) | 34.7 |
| EuroEval Icelandic Common Sense Reasoning | 1.39 | Common Sense Reasoning Average Score (%) | 26.9 |
| Icelandic LLM - WinoGrande-IS | 56.53 | Score (%) | 24.2 |
| EuroEval Norwegian NLU - Norquad | 22.37 | Reading comprehension Score (%) | 20.4 |
| EuroEval Faroese NLU - FONE | 36.75 | Named entity recognition Score (%) | 19.5 |
| EuroEval Faroese NLU - FoQA | 6.96 | Reading comprehension Score (%) | 18.4 |
| EuroEval Icelandic NLU | 13.61 | NLU Average Score (%) | 18.1 |
| EuroEval Swedish NLU - Multi Wiki QA SV | 17.03 | Reading comprehension Score (%) | 17.8 |
| EuroEval Icelandic NLU - ScaLA IS | 0 | Linguistic acceptability Score (%) | 17.4 |
| EuroEval Icelandic NLU - MIM-GOLD NER | 16.61 | Named entity recognition Score (%) | 16.9 |
| EuroEval Icelandic NLU - Hotter and Colder Sentiment | 4.54 | Sentiment classification Score (%) | 16.8 |
| EuroEval Norwegian | 8.14 | Average Score (%) | 16 |
Interactive version: theaggregate.ai/model?slug=gpt-sw3-356m-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.