EuroEval Lithuanian NLU - WikiANN LT: leaderboard
The "WikiANN LT" subtask of EuroEval Lithuanian NLU. Lithuanian-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: Micro F1 excluding MISC (%). Source: euroeval.com. Saturation forecast: Around January 2027. 230 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 71.03 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 2 | GLM 4.5 Air (Thinking) | 70.41 | #392 (GLM 4.5 Air) |
| 3 | Llama 3.1 70B | 70.1 | #592 |
| 4 | Claude Sonnet 4.5 (Thinking) | 69.92 | #142 (Claude Sonnet 4.5) |
| 5 | gemma-3-27B-pt | 69.51 | #502 |
| 6 | Claude Sonnet 4.5 (Non-reasoning) | 68.55 | #142 (Claude Sonnet 4.5) |
| 7 | Voxtral-Small-24B-2507 | 68.39 | #581 |
| 8 | GPT-5.4 Mini (2026-03-17) (High) | 68.36 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 9 | Mistral Small 3.2 | 67.61 | #605 |
| 10 | Gemma 4 31B (IT) | 67.18 | #176 |
| 11 | GPT-5 | 67.12 | #98 |
| 12 | Mistral Small 3.1 | 67.09 | #610 |
| 13 | Qwen 3 Next 80B A3B Instruct | 66.42 | #368 |
| 14 | Llama 3.3 70B Instruct | 66.31 | #534 |
| 15 | Qwen 3 235B A22B 2507 Instruct | 66.15 | #300 |
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-wikiann-lt · How It Works · Data refreshed daily, snapshot 2026-10-20.