Ukrainian LLM - ARC Challenge UK: leaderboard
The "ARC Challenge UK" 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: Estimated already saturated. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 4 26B A4B (IT) (Reasoning) | 92.49 | #297 (Gemma 4 26B A4B (IT)) |
| 2 | MamayLM-Gemma-3-12B-IT-v1.0 | 84.9 | #584 |
| 3 | Qwen3-8B-Base | 83.7 | #626 |
| 4 | lapa-v0.1.2-instruct | 71.08 | #672 |
| 5 | Llama 3.1 8B Instruct | 66.38 | #1035 |
| 6 | Gemma 3 12B (IT) | 52.3 | #664 |
| 7 | Gemma 3 4B (IT) | 45.48 | #992 |
| 8 | lapa-12B-pt | 19.2 | #1002 |
| 9 | Llama 3.1 8B | 16.98 | #1151 |
| 10 | gemma-3-12B-pt | 0.09 | #686 |
| 11 | gemma-3-4B-pt Base | 0 | #1134 |
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-arc-challenge-uk · How It Works · Data refreshed daily, snapshot 2026-10-20.