EuroEval Albanian NLU - WikiANN SQ: leaderboard
The "WikiANN SQ" subtask of EuroEval Albanian NLU. Albanian-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. 200 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 Mini (2026-03-17) (High) | 81.55 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 2 | Claude Sonnet 4.5 (Thinking) | 81.3 | #142 (Claude Sonnet 4.5) |
| 3 | Qwen 3.5 27B FP8 | 81.16 | #164 |
| 4 | Gemini 3.1 Pro (Preview) | 80.88 | #58 |
| 5 | Gemma 4 31B (IT) | 80.13 | #176 |
| 6 | Gemini 3 Pro (Preview) | 79.6 | #66 |
| 7 | gemma-3-27B-pt | 79.15 | #502 |
| 8 | GLM-4.7 Flash | 79.08 | #509 |
| 9 | gemma-3-12B-pt | 78.97 | #686 |
| 10 | Mistral Small 3.2 | 78.7 | #605 |
| 11 | GPT-5 | 78.58 | #98 |
| 12 | Qwen 3.5 35B A3B FP8 | 78.38 | #362 |
| 13 | Gemini 3 Flash (Preview) (Thinking) | 78.34 | #82 (Gemini 3 Flash (Preview)) |
| 14 | Gemma 4 26B A4B (IT) | 78.33 | #297 |
| 15 | Qwen3.5-4B-Base | 78.05 | #798 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-albanian-nlu-wikiann-sq · How It Works · Data refreshed daily, snapshot 2026-10-20.