LLM Stats (Artificial Analysis): leaderboard
LLM Stats mirror of the Artificial Analysis composite leaderboard score, condensing Artificial Analysis's evaluation of model capability into a single index.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Around 2029. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 59 | #19 |
| 2 | GLM-5.3 Flash | 57 | #65 |
| 3 | Gemini 3.7 Flash | 56 | #23 |
| 4 | Muse Wonder Full | 56 | #10 |
| 5 | GPT-5.6 Terra | 55 | #41 |
| 6 | Grok 4.5 | 54 | #48 |
| 7 | Muse Wonder | 52 | #15 |
| 8 | GPT-5.6 Luna | 51 | #68 |
| 9 | MiniMax-M2.7 | 50 | #258 |
| 10 | Inkling Small | 40 | #138 |
| 11 | Muse Spark Open | 39 | #54 |
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-artificial-analysis · How It Works · Data refreshed daily, snapshot 2026-10-20.