EuroEval Italian NLU - MultiNERD IT: leaderboard
The "MultiNERD IT" subtask of EuroEval Italian NLU. Italian-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. 429 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 88.01 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 2 | Qwen 3 4B 2507 (Thinking) | 87.46 | #538 (Qwen 3 4B 2507) |
| 3 | Llama 3.1 405B Instruct FP8 | 85.35 | #389 |
| 4 | Qwen 3 Next 80B A3B (Thinking) | 85.32 | #320 (Qwen 3 Next 80B A3B) |
| 5 | Qwen 3 30B A3B | 84.97 | #493 |
| 6 | Llama 3 70B | 84.06 | #631 |
| 7 | Llama 3.1 70B Instruct | 83.94 | #561 |
| 8 | Claude Sonnet 4.5 (Thinking) | 83.37 | #142 (Claude Sonnet 4.5) |
| 9 | Llama 3.3 70B Instruct | 83.25 | #534 |
| 10 | Voxtral-Small-24B-2507 | 83.2 | #581 |
| 11 | Llama 3.1 70B | 82.88 | #592 |
| 12 | QwQ-32B | 82.7 | #421 |
| 13 | Mistral Small 3.2 | 82.6 | #605 |
| 14 | GLM 4.5 Air (Thinking) | 82.52 | #392 (GLM 4.5 Air) |
| 15 | Magistral Small 1.2 | 81.32 | #570 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-italian-nlu-multinerd-it · How It Works · Data refreshed daily, snapshot 2026-10-20.