EuroEval Norwegian Knowledge - NRK Quiz QA: leaderboard
Multiple-choice quiz questions from the Norwegian public broadcaster NRK (NRK Quiz QA). One of the two datasets averaged into EuroEval's knowledge score for this language; few-shot by default, with some zero-shot and validation-split runs; Matthews correlation x100 as the primary metric (signed, chance 0), higher is better.
Metric: MCC (x100). Source: euroeval.com. Saturation forecast: Estimated already saturated. 438 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 89.22 | #105 |
| 2 | Gemini 2.5 Pro | 87.89 | #159 |
| 3 | Gemini 3 Pro (Preview) | 87.8 | #71 |
| 4 | Gemini 3 Flash (Preview) (Non-reasoning) | 87.73 | #90 (Gemini 3 Flash (Preview)) |
| 5 | Gemini 3 Flash (Preview) (Thinking) | 87.62 | #90 (Gemini 3 Flash (Preview)) |
| 6 | GPT-5 (2025-08-07) (High) | 86.59 | |
| 7 | O3 (2025-04-16) | 83.33 | #125 |
| 8 | Gemini 2.5 Pro (Preview 03-25) | 82.9 | #126 |
| 9 | GPT-4.1 | 82.5 | #258 |
| 10 | GPT-5.4 Mini (2026-03-17) (High) | 80.99 | #180 (GPT-5.4 Mini (2026-03-17)) |
| 11 | Gemini 2.5 Flash (Thinking) | 79.7 | #255 (Gemini 2.5 Flash) |
| 12 | Gemini 3.1 Flash Lite (Preview) | 78.26 | #201 |
| 13 | Gemini 2.5 Flash (Preview 04-17) | 77.96 | #246 |
| 14 | Claude 3.7 Sonnet (20250219) (Thinking) | 77.8 | #209 (Claude 3.7 Sonnet (20250219)) |
| 15 | GPT-4o (2024-05-13) | 77.71 | #337 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-norwegian-knowledge-nrk-quiz-qa · How It Works · Data refreshed daily, snapshot 2026-11-05.