EKI Estonian LLM - Language Advice: leaderboard
EKI language-advice benchmark: 240 questions on Estonian orthography, inflected forms and word choice based on real queries to EKI's language advice service, mixing true/false, multiple-choice, short-answer and judge-graded open questions. Accuracy 0-100, higher is better.
Metric: Accuracy (%). Source: moodupuu.eki.ee. Saturation forecast: Around May 2028. 100 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon | 77.5 | #9 |
| 2 | GPT-6 Astra | 76.04 | #6 |
| 3 | Claude Fable 5 | 74.79 | #20 |
| 4 | Claude Fable 5.1 | 72.71 | #10 |
| 5 | GPT-6.1 Terra | 70.62 | #15 |
| 6 | Claude Opus 5.5 | 68.75 | #3 |
| 7 | GPT-6 Sol | 67.08 | #19 |
| 8 | Gemini 3.8 Flash | 66.88 | #30 |
| 9 | Gemini 3.7 Flash | 66.46 | #24 |
| 10 | GPT-5.6 Sol | 66.25 | #22 |
| 11 | Claude Opus 5 | 65.42 | #16 |
| 12 | GPT-5.5 | 65.21 | #33 |
| 13 | Gemini 3 Flash (Preview) | 64.58 | #90 |
| 14 | GPT-6 Luna | 63.75 | #61 |
| 15 | Claude Sonnet 5.5 | 62.5 | #14 |
No result here: #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=eki-estonian-llm-language-advice · How It Works · Data refreshed daily, snapshot 2026-11-05.