EuroEval English NLU - ScaLA EN: leaderboard
The "ScaLA EN" 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: Around January 2027. 334 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 76.44 | #90 |
| 2 | Gemini 3.1 Flash Lite (Preview) | 71.39 | #194 |
| 3 | Gemini 3 Flash (Preview) (Thinking) | 69.31 | #82 (Gemini 3 Flash (Preview)) |
| 4 | Gemini 3 Flash (Preview) (Non-reasoning) | 68.65 | #82 (Gemini 3 Flash (Preview)) |
| 5 | Grok 4.1 Fast (Reasoning) | 68.02 | #217 (Grok 4.1 Fast) |
| 6 | NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 67.64 | #679 |
| 7 | Gemini 3 Pro (Preview) | 67.31 | #66 |
| 8 | Gemma 4 31B (IT) | 67.13 | #176 |
| 9 | GPT-5.2 | 66.75 | #110 |
| 10 | Qwen 3.5 35B A3B FP8 | 65.59 | #362 |
| 11 | GPT-5.4 Mini (2026-03-17) (High) | 65.16 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 12 | Nemotron Cascade 2 30B A3B | 65.16 | #551 |
| 13 | GPT-5.4 Nano (2026-03-17) (High) | 65.14 | #266 (GPT-5.4 Nano (2026-03-17)) |
| 14 | Llama 3.1 405B | 64.62 | #466 |
| 15 | Gemma 4 26B A4B (IT) | 64 | #297 |
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-scala-en · How It Works · Data refreshed daily, snapshot 2026-10-20.