EuroEval Lithuanian NLU - Atsiliepimai: leaderboard
The "Atsiliepimai" subtask of EuroEval Lithuanian NLU. Lithuanian-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: Matthews correlation coefficient (%). Source: euroeval.com. Saturation forecast: Around May 2027. 202 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 4 31B (IT) | 50.67 | #176 |
| 2 | Ministral-3-14B-Instruct-2512 | 50.64 | #615 |
| 3 | Gemini 2.5 Flash Lite (Non-reasoning) | 50.18 | #422 (Gemini 2.5 Flash Lite) |
| 4 | Gemma 4 26B A4B (IT) | 50.01 | #297 |
| 5 | Ministral-3-14B-Reasoning-2512 | 49.77 | #540 |
| 6 | Ministral-3-8B-Instruct-2512 | 49.76 | #661 |
| 7 | gemma-4-E4B-it | 49.2 | #566 |
| 8 | Voxtral-Small-24B-2507 | 48.87 | #581 |
| 9 | gemma-3-12B-pt | 48.31 | #686 |
| 10 | Qwen 2.5 72B Instruct | 48.29 | #454 |
| 11 | gemma-3-27B-pt | 48.2 | #502 |
| 12 | Claude Sonnet 4.6 | 47.92 | #90 |
| 13 | gemma-3-4B-pt Base | 47.92 | #1134 |
| 14 | Gemma 3 12B (IT) | 47.8 | #664 |
| 15 | Qwen 3.5 35B A3B Base | 47.76 | #310 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-lithuanian-nlu-atsiliepimai · How It Works · Data refreshed daily, snapshot 2026-10-20.