EuroEval Catalan NLU - WikiANN CA: leaderboard
The "WikiANN CA" subtask of EuroEval Catalan NLU. Catalan-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. 212 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | OLMo 3.1 32B (Thinking) | 75.06 | #632 (OLMo 3.1 32B) |
| 2 | gemma-3-27B-pt | 74.85 | #502 |
| 3 | gemma-3-12B-pt | 74.82 | #686 |
| 4 | Mistral Small 3.2 | 74.29 | #605 |
| 5 | Llama 3.1 70B | 74.17 | #592 |
| 6 | Bielik-11B-v2.3-Instruct | 73.71 | #693 |
| 7 | Qwen3.5-4B-Base | 73.68 | #798 |
| 8 | Qwen 3.5 27B FP8 | 73.46 | #164 |
| 9 | Ministral-3-14B-Reasoning-2512 | 73.19 | #540 |
| 10 | Voxtral-Small-24B-2507 | 72.79 | #581 |
| 11 | SOLAR-10.7B-v1.0 | 72.32 | #1253 |
| 12 | Qwen 3.5 35B A3B FP8 | 72.32 | #362 |
| 13 | Gemma 4 26B A4B (IT) | 71.79 | #297 |
| 14 | Claude Sonnet 4.5 (Thinking) | 71.77 | #142 (Claude Sonnet 4.5) |
| 15 | Gemma 4 31B (IT) | 71.6 | #176 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-catalan-nlu-wikiann-ca · How It Works · Data refreshed daily, snapshot 2026-10-20.