Evals for Every Language - Georgian (ka): leaderboard
Average score across evaluation tasks in Georgian (ka), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 65 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 74.8 | #37 |
| 2 | Gemini 3.1 Pro (Preview) | 74.41 | #58 |
| 3 | GPT-5 | 74.15 | #98 |
| 4 | GPT-5.1 | 74.06 | #135 |
| 5 | Claude Sonnet 4 | 73.77 | #199 |
| 6 | Grok 4.20 | 73.4 | #175 |
| 7 | Claude Sonnet 4.5 | 72.83 | #142 |
| 8 | Claude Haiku 4.5 | 72.49 | #280 |
| 9 | DeepSeek V3.2 Exp | 72.42 | #234 |
| 10 | GPT-4o | 72.36 | #343 |
| 11 | Llama 4 Maverick | 72.09 | #464 |
| 12 | Qwen 3.6 Plus | 71.55 | #120 |
| 13 | Claude Opus 4.7 | 71.48 | #49 |
| 14 | GPT-5.5 | 71.25 | #31 |
| 15 | Gemini 3.1 Flash Lite | 71.16 | #191 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-ka · How It Works · Data refreshed daily, snapshot 2026-10-20.