EKI Estonian LLM - Overall: leaderboard
Keelemudelite mõõdupuu, the Institute of the Estonian Language's independent Estonian leaderboard: unweighted mean of its benchmark scores (seven at launch of this board), 0-100, higher is better. As on the site, only models evaluated on every published benchmark are included; models run without web search or tools.
Metric: Mean benchmark score (0-100). Source: moodupuu.eki.ee. Saturation forecast: Around July 2027. 92 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 74.32 | #6 |
| 2 | GPT-5.6 Sol | 71.26 | #22 |
| 3 | Gemini 4 Argon | 69.81 | #9 |
| 4 | Gemini 3.1 Pro (Preview) | 69.52 | #64 |
| 5 | GPT-6 Sol | 69.16 | #19 |
| 6 | Gemini 3.8 Flash | 68.9 | #30 |
| 7 | Claude Fable 5 | 68.53 | #20 |
| 8 | Gemini 3.7 Flash | 68.22 | #24 |
| 9 | GPT-5.5 | 68.04 | #33 |
| 10 | Claude Fable 5.1 | 67.94 | #10 |
| 11 | GPT-6.1 Terra | 67.57 | #15 |
| 12 | Claude Opus 5 | 64.1 | #16 |
| 13 | Claude Opus 5.5 | 63.68 | #3 |
| 14 | Gemini 3.5 Flash | 62.89 | #66 |
| 15 | Grok 4.7 | 62.23 | #26 |
No result here: #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=eki-estonian-llm-overall · How It Works · Data refreshed daily, snapshot 2026-11-05.