EuroEval English: leaderboard
English LLM evaluation across 7 tasks: sentiment, NER, linguistic acceptability, reading comprehension, summarization, knowledge, and common-sense reasoning.
Metric: Average Score (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 343 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.1 405B | 79.72 | #466 |
| 2 | GPT-5 (2025-08-07) (High) | 79.09 | |
| 3 | Qwen 3 235B A22B 2507 Instruct | 78.94 | #300 |
| 4 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 77.99 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 5 | Llama 3.1 405B Instruct FP8 | 77.88 | #389 |
| 6 | Qwen 3 Next 80B A3B Instruct | 77.61 | #368 |
| 7 | O3 (2025-04-16) | 77.37 | #121 |
| 8 | Magistral Small 1.2 | 77.21 | #570 |
| 9 | GPT-5 | 77.16 | #98 |
| 10 | Yi 1.5 34B | 77.14 | #807 |
| 11 | Gemini 3 Flash (Preview) (Thinking) | 77.08 | #82 (Gemini 3 Flash (Preview)) |
| 12 | Claude 3.7 Sonnet (20250219) (Thinking) | 76.61 | #201 (Claude 3.7 Sonnet (20250219)) |
| 13 | Qwen 3 235B A22B | 76.45 | #313 |
| 14 | Gemini 3 Flash (Preview) (Non-reasoning) | 76.36 | #82 (Gemini 3 Flash (Preview)) |
| 15 | Mistral Small 3 | 76.05 | #627 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-english · How It Works · Data refreshed daily, snapshot 2026-10-20.