LLM Stats (ECLeKTic): leaderboard
Long-context knowledge comprehension across 14 diverse topics and 23 languages, requiring accurate information extraction from 10K–300K token documents.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Around January 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 3 27B | 16.7 | #607 |
| 2 | Gemma 3 12B | 10.3 | #671 |
| 3 | Gemma 3 4B | 4.6 | #1089 |
| 4 | gemma-3n-E2B-it Instruct | 2.5 | #1322 |
| 5 | Gemma 3 1B | 1.4 | #1528 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-eclektic · How It Works · Data refreshed daily, snapshot 2026-10-20.