EuroEval Lithuanian NLU - WikiANN LT — leaderboard
Metric: Named entity recognition Score (%). Source: euroeval.com. 230 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.1 70B | 70.1 |
| 2 | Claude Sonnet 4.5 (Thinking) | 69.92 |
| 3 | gemma-3-27B-pt | 69.51 |
| 4 | Claude Sonnet 4.5 (Non-reasoning) | 68.55 |
| 5 | GPT-5.4 Mini (High) | 68.36 |
| 6 | GPT-5.4 Mini (Medium) | 67.66 |
| 7 | Mistral Small 3.2 | 67.61 |
| 8 | Gemma 4 31B (IT) | 67.18 |
| 9 | GPT-5 | 67.12 |
| 10 | Mistral Small 3.1 | 67.09 |
| 11 | Qwen 3 Next 80B A3B Instruct | 66.42 |
| 12 | Llama 3.3 70B Instruct | 66.31 |
| 13 | Ministral 3 14B | 66.18 |
| 14 | Qwen 3 235B A22B 2507 Instruct | 66.15 |
| 15 | Qwen 3 Next 80B A3B (Thinking) | 65.98 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-lithuanian-nlu-wikiann-lt · How the rankings work · Data refreshed daily, snapshot 2026-07-22.