EuroEval Icelandic: leaderboard

Metric: Average Score (%). Source: euroeval.com. 401 models tracked.

Top models

#ModelScore
1GPT-570.59
2GPT-5 (High)68.61
3Gemini 3 Pro (Preview)68.02
4O3 (2025-04-16)66.08
5Gemini 2.5 Pro65.81
6Gemini 2.5 Pro (Preview 03-25)64.33
7Gemini 2.5 Flash (Thinking)62.64
8Gemini 2.5 Flash (Preview 04-17)61.64
9Claude 3.7 Sonnet (20250219) (Thinking)61.61
10Claude Sonnet 4.5 (Thinking)60.67
11GPT-5.4 Mini (High)60.51
12GPT-5 Mini (High)60.19
13Gemini 3.1 Flash Lite (Preview)59.64
14GPT-5.4 Mini (Medium)59.56
15O4 Mini (2025-04-16)57.85

Interactive version: theaggregate.ai/benchmark?slug=euroeval-icelandic · How It Works · Data refreshed daily, snapshot 2026-09-05.