EuroEval Icelandic Common Sense Reasoning: leaderboard

EuroEval's Icelandic common-sense reasoning task — multiple-choice questions testing everyday physical and social reasoning in Icelandic, from the EuroEval European language model benchmark suite.

Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. Saturation forecast: Around February 2027. 324 models tracked.

Top models

#ModelScoreOverall rank
1GPT-595.1#98
2Gemini 2.5 Pro92.47#152
3Gemini 3 Pro (Preview)89.84#66
4O3 (2025-04-16)89.24#121
5GPT-5 (2025-08-07) (High)89.2
6Gemini 2.5 Pro (Preview 03-25)88.43#123
7Claude Sonnet 4.5 (Thinking)88.1#142 (Claude Sonnet 4.5)
8Gemini 2.5 Flash (Preview 04-17)86.14#237
9GPT-5 Mini (2025-08-07) (High)85.66#172 (GPT-5 Mini (2025-08-07))
10Gemini 2.5 Flash (Thinking)81.9#245 (Gemini 2.5 Flash)
11Grok 4.1 Fast (Reasoning)81.87#217 (Grok 4.1 Fast)
12GPT-5 Mini (2025-08-07)80.19#172
13Gemini 3 Flash (Preview) (Thinking)80.04#82 (Gemini 3 Flash (Preview))
14GPT-5.4 Mini (2026-03-17) (High)78.79#169 (GPT-5.4 Mini (2026-03-17))
15Claude 3.7 Sonnet (20250219) (Thinking)76.58#201 (Claude 3.7 Sonnet (20250219))

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=euroeval-icelandic-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.