EuroEval Italian: leaderboard
Italian-language EuroEval all-task suite spanning NLU, knowledge, common-sense reasoning, reading comprehension, summarization, and related tasks.
Metric: Average Score (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 435 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 73.12 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 2 | Gemini 3 Pro (Preview) | 72.45 | #66 |
| 3 | Gemma 4 31B (IT) | 71.18 | #176 |
| 4 | Claude Sonnet 4.6 | 70.59 | #90 |
| 5 | Gemini 3 Flash (Preview) (Thinking) | 70.26 | #82 (Gemini 3 Flash (Preview)) |
| 6 | Gemini 3 Flash (Preview) (Non-reasoning) | 69.82 | #82 (Gemini 3 Flash (Preview)) |
| 7 | Gemini 3.1 Flash Lite (Preview) | 69.46 | #194 |
| 8 | Qwen 3 235B A22B 2507 Instruct | 68.86 | #300 |
| 9 | GPT-5 (2025-08-07) (High) | 68.09 | |
| 10 | GPT-5 | 67.88 | #98 |
| 11 | GPT-5.4 Mini (2026-03-17) (High) | 67.32 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 12 | Claude Sonnet 4.5 (Thinking) | 67.31 | #142 (Claude Sonnet 4.5) |
| 13 | Qwen 3 Next 80B A3B Instruct | 67.31 | #368 |
| 14 | Llama 3.1 405B Instruct FP8 | 67.23 | #389 |
| 15 | Qwen 3 Next 80B A3B (Thinking) | 66.99 | #320 (Qwen 3 Next 80B A3B) |
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 · How It Works · Data refreshed daily, snapshot 2026-10-20.