Icelandic LLM - Textile Terms: leaderboard
Metric: LLM Judge Score (%). Source: huggingface.co. 24 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-6 | 74 |
| 2 | Gemini 3.8 Flash | 71.8 |
| 3 | GPT-5.6 Sol | 68.2 |
| 4 | Claude Opus 5 | 68 |
| 5 | Gemini 3.7 Flash | 67.8 |
| 6 | Claude Fable 5.1 | 67.8 |
| 7 | Gemini 3.1 Pro (Preview) | 67.2 |
| 8 | Gemini 3.5 Flash | 65.2 |
| 9 | Claude Opus 4.8 | 63.9 |
| 10 | GPT-5.6 Luna | 60.7 |
| 11 | GPT-5.6 Terra | 60.1 |
| 12 | DeepSeek V4 Pro | 57.8 |
| 13 | Gemini 2.5 Pro | 57.5 |
| 14 | GPT-5.2 | 57.4 |
| 15 | Gemini 3.5 Flash Lite | 55.8 |
Interactive version: theaggregate.ai/benchmark?slug=icelandic-llm-textile-terms · How It Works · Data refreshed daily, snapshot 2026-09-19.