EuroEval Estonian NLU - MultiWikiQA ET: leaderboard
The "MultiWikiQA ET" subtask of EuroEval Estonian NLU. Estonian-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: Around January 2027. 249 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Ministral-3-14B-Reasoning-2512 | 77.98 | #540 |
| 2 | Qwen3.5-4B-Base | 75.36 | #798 |
| 3 | Mistral Small 3.2 | 74.85 | #605 |
| 4 | Llama 3.1 70B | 74.85 | #592 |
| 5 | gemma-3-27B-pt | 74.74 | #502 |
| 6 | Magistral Small 1.2 | 74.15 | #570 |
| 7 | Ministral-3-14B-Instruct-2512 | 73.2 | #615 |
| 8 | Mistral Small 3.1 | 72.91 | #610 |
| 9 | gemma-3-12B-pt | 72.46 | #686 |
| 10 | Qwen 2.5 72B Instruct | 72.35 | #454 |
| 11 | Voxtral-Small-24B-2507 | 72.28 | #581 |
| 12 | Gemma 4 31B | 71.88 | #200 |
| 13 | Qwen 3 32B (Non-reasoning) | 70.94 | #443 (Qwen 3 32B) |
| 14 | Qwen 3 14B (Non-reasoning) | 70.89 | #537 (Qwen 3 14B) |
| 15 | Llama 3.1 8B | 70.34 | #1151 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-estonian-nlu-multiwikiqa-et · How It Works · Data refreshed daily, snapshot 2026-10-20.