EKI Estonian LLM - Terminology: leaderboard
EKI terminology benchmark: 1,380 definition-to-term questions, 30 terms in each of 46 specialist fields from the Esterm term base and field term collections; an answer must give the term or a registered synonym. Accuracy 0-100, higher is better.
Metric: Accuracy (%). Source: moodupuu.eki.ee. Saturation forecast: Around November 2027. 100 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 61.81 | #6 |
| 2 | GPT-5.5 | 59.13 | #33 |
| 3 | Gemini 3.8 Flash | 57.68 | #30 |
| 4 | Gemini 4 Argon | 57.54 | #9 |
| 5 | GPT-6 Sol | 57.54 | #19 |
| 6 | Gemini 3.7 Flash | 57.25 | #24 |
| 7 | Gemini 3.1 Pro (Preview) | 57.03 | #64 |
| 8 | GPT-5.6 Sol | 56.59 | #22 |
| 9 | Claude Opus 5.5 | 56.45 | #3 |
| 10 | Claude Fable 5.1 | 56.09 | #10 |
| 11 | Claude Opus 5 | 55.94 | #16 |
| 12 | GPT-6.1 Terra | 55.29 | #15 |
| 13 | Claude Fable 5 | 55.22 | #20 |
| 14 | Gemini 3.5 Flash | 54.13 | #66 |
| 15 | Grok 4.7 | 52.68 | #26 |
No result here: #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=eki-estonian-llm-terminology · How It Works · Data refreshed daily, snapshot 2026-11-05.