Ukrainian LLM - Global MMLU Full UK Machine Learning: leaderboard
The "Global MMLU Full UK Machine Learning" subtask of Ukrainian LLM. A task from the Ukrainian LLM Leaderboard, evaluating models on Ukrainian-language understanding, knowledge and reasoning.
Metric: Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen3-8B-Base | 59.82 | #626 |
| 2 | gemma-3-12B-pt | 51.79 | #686 |
| 3 | lapa-12B-pt | 46.43 | #1002 |
| 4 | MamayLM-Gemma-3-12B-IT-v1.0 | 44.64 | #584 |
| 5 | Gemma 3 12B (IT) | 41.96 | #664 |
| 6 | lapa-v0.1.2-instruct | 41.07 | #672 |
| 7 | Llama 3.1 8B | 37.5 | #1151 |
| 8 | gemma-3-4B-pt Base | 35.71 | #1134 |
| 9 | Llama 3.1 8B Instruct | 32.14 | #1035 |
| 10 | Gemma 3 4B (IT) | 27.68 | #992 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=ukrainian-llm-global-mmlu-full-uk-machine-learning · How It Works · Data refreshed daily, snapshot 2026-10-20.