gpt-sw3-126m-instruct — benchmark results
Provider: AI Sweden. Released 2023-04-28. Access: Open.
Unified ELO 1019 ± 43, rank #1772 of 1776 rated models, from 94 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Icelandic NLU - ScaLA IS | 2.31 | Linguistic acceptability Score (%) | 45.8 |
| EuroEval Icelandic Common Sense Reasoning | 0.59 | Common Sense Reasoning Average Score (%) | 19.8 |
| EuroEval Icelandic NLU - MIM-GOLD NER | 17.85 | Named entity recognition Score (%) | 18.7 |
| Icelandic LLM - WinoGrande-IS | 53.86 | Score (%) | 18.7 |
| Icelandic LLM - GED | 51 | Score (%) | 17 |
| EuroEval Danish NLU - Angry Tweets | 17.37 | Sentiment classification Score (%) | 16.3 |
| EuroEval Faroese NLU - ScaLA FO | 0 | Linguistic acceptability Score (%) | 15.9 |
| EuroEval Norwegian | 8.13 | Average Score (%) | 15.8 |
| EuroEval Dutch Common Sense Reasoning | 0.69 | Common Sense Reasoning Average Score (%) | 14.8 |
| EuroEval Faroese NLU - FONE | 29.27 | Named entity recognition Score (%) | 14.7 |
| EuroEval Norwegian NLU - Norquad | 9.58 | Reading comprehension Score (%) | 14.4 |
| EuroEval Icelandic NLU - Hotter and Colder Sentiment | 3.39 | Sentiment classification Score (%) | 14 |
Interactive version: theaggregate.ai/model?slug=gpt-sw3-126m-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.