Kaz-LLM - MMLU (Kazakh) — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 74.2 |
| 2 | Gemini 1.5 Pro | 73.81 |
| 3 | Claude 3.5 Sonnet | 73.35 |
| 4 | Nova Pro (v1) | 67.93 |
| 5 | Gemini 1.5 Flash | 63.36 |
| 6 | GPT-4o Mini | 56.24 |
Interactive version: aibenchmarks.dev/benchmark?slug=kaz-llm-mmlu-kazakh · How the rankings work · Data refreshed daily, snapshot 2026-07-08.