Icelandic LLM - Case Government: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 24 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 | 99.06 |
| 2 | Gemini 3.8 Flash | 98.75 |
| 3 | Gemini 3.7 Flash | 98.44 |
| 4 | Gemini 3.1 Pro (Preview) | 97.81 |
| 5 | Gemini 3.5 Flash | 97.5 |
| 6 | GPT-6 | 96.56 |
| 7 | Claude Fable 5.1 | 96.25 |
| 8 | Claude Opus 4.8 | 95.94 |
| 9 | GPT-5.6 Sol | 95.31 |
| 10 | Claude Sonnet 5 | 89.06 |
| 11 | Gemini 3.5 Flash Lite | 88.12 |
| 12 | Gemini 2.5 Pro | 84.06 |
| 13 | GPT-5.2 | 78.44 |
| 14 | DeepSeek V4 Pro | 78.44 |
| 15 | GPT-5.6 Terra | 75 |
Interactive version: theaggregate.ai/benchmark?slug=icelandic-llm-case-government · How It Works · Data refreshed daily, snapshot 2026-09-19.