EuroEval Finnish NLU - Tydiqa FI: leaderboard

The "Tydiqa FI" subtask of EuroEval Finnish NLU. Finnish-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.

Metric: Character F1 (%). Source: euroeval.com. Saturation forecast: Not forecast. 374 models tracked.

Top models

#ModelScoreOverall rank
1Qwen3.5-4B-Base77.51#799
2EuroLLM-9B77.33#1237
3Gemma 2 27B77.11#805
4Llama 3 70B77.11#634
5Llama 3.1 70B76.96#591
6Ministral-3-14B-Reasoning-251276.61#557
7Magistral Small 1.276.47#605
8Llama 2 70B76.05#1044
9Yi 1.5 34B75.98#806
10SOLAR-10.7B-v1.075.92#1244
11Gemma 3n E4B75.84#882
12gemma-3-27B-pt75.66#506
13Mistral Small 3.274.97#608
14Bielik-11B-v2.3-Instruct74.94#701
15Mistral Small 3.174.86#625

No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #6 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=euroeval-finnish-nlu-tydiqa-fi · How It Works · Data refreshed daily, snapshot 2026-11-06.