Icelandic LLM - WikiQA-IS — leaderboard

Metric: Score (%). Source: huggingface.co. 92 models tracked.

Top models

#ModelScore
1Claude Fable 575.39
2Gemini 3.1 Pro (Preview)67.74
3Gemini 3 Pro (Preview)64.82
4Gemini 3.5 Flash64.68
5GPT-5.6 Sol63.21
6Claude Opus 4.862.42
7Gemini 3 Flash (Preview)61.47
8Claude Opus 4.759.42
9GPT-5.559.18
10Gemini 2.5 Pro (03-25)52.66
11GPT-5.4 (2026-03-05)49.45
12Gemini 3.1 Flash Lite (Preview)48.18
13GPT-5.6 Luna46.87
14GPT-5.6 Terra46.18
15GPT-545.79

Interactive version: theaggregate.ai/benchmark?slug=icelandic-llm-wikiqa-is · How the rankings work · Data refreshed daily, snapshot 2026-07-22.