Artificial Analysis Intelligence (October 2026)
In October 2026, Claude Fable 5.1 ranks first with 61.3, followed by Muse Spark 1.3 (59.3) and Claude Opus 5 (59.2). Top 20 of 486 candidates.
Data as of October 2026
| # | Model | Provider | Score | Intelligence |
|---|---|---|---|---|
| 1 |  Claude Fable 5.1 | Anthropic | 61.3 | 53.4 |
| 2 |  Muse Spark 1.3 | Meta | 59.3 | 62.1 |
| 3 | Claude Opus 5 | Anthropic | 59.2 | 50.8 |
| 4 |  GLM-5.3 | Zhipu AI | 59.1 | 44.8 |
| 5 |  Grok 4.6 | xAI | 58.7 | 44.3 |
| 6 | GLM-5.3-Flash | Zhipu AI | 58.2 | 41.8 |
| 7 |  GPT-5.6 Sol (max) | OpenAI | 57.8 | 47.0 |
| 8 |  Qwen3.8 2.4T A95B | Alibaba | 57.1 | 39.9 |
| 9 | Claude Fable 5 | Anthropic | 56.6 | 49.6 |
| 10 | Qwen3.8-Flash-Next | Alibaba | 56.4 | 39.8 |
| 11 |  Kimi K3 (max) | Moonshot | 54.3 | 43.6 |
| 12 | GPT-5.6 Sol (xhigh) | OpenAI | 53.6 | 44.0 |
| 13 |  DeepSeek V4 Flash Vision (Reasoning, Max Effort) | DeepSeek | 52.9 | 34.8 |
| 14 | Qwen 3.8 27B | Alibaba | 50.9 | 33.7 |
| 15 | GPT-5.6 Sol (high) | OpenAI | 50.6 | 42.3 |
| 16 | GPT-5.6 Terra (max) | OpenAI | 50.2 | 42.1 |
| 17 |  Gemini 3.8 Flash | 50.0 | 40.9 | |
| 18 | Claude Sonnet 5 | Anthropic | 49.7 | 38.2 |
| 19 | DeepSeek-V4-Pro-0813 | DeepSeek | 49.6 | 36.0 |
| 20 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | Anthropic | 49.4 | 41.8 |
How this chart is built
Draws on a leading third-party evaluation programme that measures model capability across standardised test sets. The chart shows its latest published scores.
Positions are renumbered from high to low by this table's own metric, independent of any ranking the source publishes. Figures are the current real data with no manual adjustment; values we cannot obtain show as “—” and are never filled in with estimates.
FAQ
Artificial Analysis Intelligence: who ranks #1?
In October 2026, Anthropic’s Claude Fable 5.1 ranks #1 (score: 61.3); Muse Spark 1.3 is second (59.3), followed by Claude Opus 5 (59.2).
Artificial Analysis Intelligence: what are the top 10?
Ranked by score as of October 2026, the top 10 are: 1. Claude Fable 5.1, 2. Muse Spark 1.3, 3. Claude Opus 5, 4. GLM-5.3, 5. Grok 4.6, 6. GLM-5.3-Flash, 7. GPT-5.6 Sol (max), 8. Qwen3.8 2.4T A95B, 9. Claude Fable 5, 10. Qwen3.8-Flash-Next. The full top 20 is in the table on this page.
Artificial Analysis Intelligence: where does the data come from, and how often is it updated?
Draws on a leading third-party evaluation programme that measures model capability across standardised test sets. The chart shows its latest published scores. Refreshed when the source publishes; the current data is dated October 1, 2026.