EuroEval Bosnian NLU - WikiANN BS: leaderboard
The "WikiANN BS" subtask of EuroEval Bosnian NLU. Bosnian-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 | Qwen 3.5 27B FP8 | 78.52 | #164 |
| 2 | Gemma 4 31B (IT) | 77.97 | #176 |
| 3 | Gemini 3.1 Pro (Preview) | 77.14 | #58 |
| 4 | Claude Sonnet 4.5 (Thinking) | 76.94 | #142 (Claude Sonnet 4.5) |
| 5 | Grok 4.20 Beta (0309) (Reasoning) | 76.5 | #204 (Grok 4.20 Beta (0309)) |
| 6 | Gemini 3 Flash (Preview) (Thinking) | 76.48 | #82 (Gemini 3 Flash (Preview)) |
| 7 | Gemma 4 26B A4B (IT) | 76.03 | #297 |
| 8 | Gemini 3 Pro (Preview) | 75.74 | #66 |
| 9 | GPT-5.4 Mini (2026-03-17) (High) | 75.55 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 10 | Gemini 2.5 Pro | 75.52 | #152 |
| 11 | Claude Sonnet 4.5 (Non-reasoning) | 75.42 | #142 (Claude Sonnet 4.5) |
| 12 | Gemini 3.1 Flash Lite (Preview) | 74.98 | #194 |
| 13 | GPT-5.2 | 74.84 | #110 |
| 14 | GPT-5 | 74.78 | #98 |
| 15 | GPT-5 Nano | 74.78 | #425 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-bosnian-nlu-wikiann-bs · How It Works · Data refreshed daily, snapshot 2026-10-20.