EuroEval English NLU - SST-5: leaderboard
The "SST-5" subtask of EuroEval English NLU. English-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: Matthews correlation coefficient (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 335 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 71.56 | #90 |
| 2 | GPT-4.1 | 71 | #248 |
| 3 | GPT-5 | 70.36 | #98 |
| 4 | Llama 3.1 405B Instruct FP8 | 70.29 | #389 |
| 5 | Gemini 3 Flash (Preview) (Non-reasoning) | 70.27 | #82 (Gemini 3 Flash (Preview)) |
| 6 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 70.26 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 7 | Claude Sonnet 4.5 (Non-reasoning) | 70.16 | #142 (Claude Sonnet 4.5) |
| 8 | QwQ-32B | 70.14 | #421 |
| 9 | Qwen 3 Next 80B A3B Instruct | 69.82 | #368 |
| 10 | cogito-v1-preview-qwen-14B | 69.81 | |
| 11 | OLMo-2-0325-32B-Instruct | 69.75 | #848 |
| 12 | gemma-3-27B-pt | 69.57 | #502 |
| 13 | OLMo-2-1124-13B-Instruct | 69.45 | #1100 |
| 14 | GLM-4.1V-9B (Thinking) | 69.38 | #472 (GLM-4.1V-9B) |
| 15 | Yi 1.5 34B | 69.38 | #807 |
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-nlu-sst-5 · How It Works · Data refreshed daily, snapshot 2026-10-20.