Turkish MMLU: leaderboard
The alibayram Turkish MMLU leaderboard evaluates 6,200 multiple-choice questions across 62 academic, professional, and general-knowledge sections. It reports the published success percentage with each run's source model size and quantization configuration.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 66 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 84.84 | #343 |
| 2 | Claude 3.5 Sonnet (20240620) | 84.4 | #299 |
| 3 | Gemini 1.5 Pro | 76.74 | #445 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=turkish-mmlu · How It Works · Data refreshed daily, snapshot 2026-10-20.