gpt-sw3-40B — benchmark results
Provider: AI Sweden. Released 2023-02-22. Access: Open.
Unified ELO 1120 ± 34, rank #1754 of 1776 rated models, from 35 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Swedish NLU - Multi Wiki QA SV | 71.21 | Reading comprehension Score (%) | 64.4 |
| EuroEval Danish NLU - Multi Wiki QA DA | 73.22 | Reading comprehension Score (%) | 61 |
| EuroEval Icelandic Common Sense Reasoning | 2.08 | Common Sense Reasoning Average Score (%) | 33 |
| EuroEval Swedish NLU - ScaLA SV | 8.21 | Linguistic acceptability Score (%) | 29.8 |
| EuroEval Swedish NLU | 41.57 | NLU Average Score (%) | 29.6 |
| EuroEval Danish NLU | 27.13 | NLU Average Score (%) | 27.9 |
| EuroEval Danish NLU - ScaLA DA | 3.72 | Linguistic acceptability Score (%) | 26.5 |
| EuroEval Danish Knowledge | 13.57 | Knowledge Average Score (%) | 24.3 |
| EuroEval Norwegian Knowledge | 3.38 | Knowledge Average Score (%) | 22.6 |
| EuroEval Norwegian Common Sense Reasoning | 5 | Common Sense Reasoning Average Score (%) | 22.4 |
| EuroEval Swedish | 26.31 | Average Score (%) | 21.7 |
| EuroEval Danish | 18.45 | Average Score (%) | 21.4 |
Interactive version: theaggregate.ai/model?slug=gpt-sw3-40b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.