Kazakh LLM - World History: leaderboard
Kazakh LLM leaderboard — accuracy on Kazakh national-exam (UNT) world history multiple-choice questions.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 67.83 | #343 |
| 2 | Gemini 1.5 Pro | 66.69 | #445 |
| 3 | Claude 3.5 Sonnet | 66.69 | #350 |
| 4 | Nova Pro (v1) | 64.25 | #497 |
| 5 | GPT-4o Mini | 60.91 | #599 |
| 6 | Gemini 1.5 Flash | 58.39 | #618 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=kazakh-llm-world-history · How It Works · Data refreshed daily, snapshot 2026-10-20.