nsanku-MMLU - Kasem: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) (Non-reasoning) | 32.65 |
| 2 | GPT-4o | 26.02 |
| 3 | DeepSeek V4 Flash (Non-reasoning) | 26.02 |
Interactive version: theaggregate.ai/benchmark?slug=nsanku-mmlu-kasem · How It Works · Data refreshed daily, snapshot 2026-09-19.