EKI Estonian LLM - Book Recommendations: leaderboard
EKI book-recommendation benchmark: 40 prompts each asking for four Estonian-language books across 8 genres and 5 criteria; every title-author pair is checked against the Estonian National Bibliography. Score is the share of recommendations matching a real book (0-100, higher is better).
Metric: Recommendations matching a real book (%). Source: moodupuu.eki.ee. Saturation forecast: Around February 2027. 100 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 90.62 | #22 |
| 2 | Claude Fable 5.1 | 90.45 | #10 |
| 3 | GPT-6 Astra | 89.38 | #6 |
| 4 | Claude Fable 5 | 89.09 | #20 |
| 5 | GPT-6.1 Terra | 88.75 | #15 |
| 6 | GPT-6 Sol | 86.25 | #19 |
| 7 | Grok 4.7 | 86.25 | #26 |
| 8 | Claude Opus 5 | 85.65 | #16 |
| 9 | Gemini 3.1 Pro (Preview) | 80.62 | #64 |
| 10 | Gemini 3.7 Flash | 80.25 | #24 |
| 11 | Claude Opus 5.5 | 79.64 | #3 |
| 12 | GPT-5.6 Terra | 77.5 | #40 |
| 13 | Muse Spark 1.3 | 77.5 | #31 |
| 14 | GPT-6 Luna | 76.88 | #61 |
| 15 | GPT-5.5 | 75.44 | #33 |
No result here: #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=eki-estonian-llm-book-recommendations · How It Works · Data refreshed daily, snapshot 2026-11-05.