Skip to content

Benchmarks · Artificial Analysis

Artificial Analysis Intelligence Index

Artificial Analysis composite index of general intelligence (reasoning, knowledge, coding, agentic work). Not legal. PrudentScore v1.1 uses version 4.3.2; Artificial Analysis moved to v5.0 on 27 October 2026 (different scale).

Models measured
23
Version
4.3.2
Measured
20 October 2026
Go to the sourceIn the PrudentScore, version 4.3.2 of this benchmark counts for 15 percent.
Versions

01

In running text

Artificial Analysis measured 23 models from the register on version 4.3.2, 14 of which pass our compliance gate. Of that group, Claude Opus 5.5 ranks highest at 57.6, position 1 of 23. Source: Artificial Analysis (artificialanalysis.ai/models), accessed 1 October 2026 [37].

Figures from this source appear in running text only, with attribution, as that party’s terms require [9]. There is no table of them.

Other benchmarks

Claude and Anthropic, GPT and OpenAI, Gemini and Google, Grok and xAI, Kimi and Moonshot AI, Muse and Meta, Mistral, DeepSeek, GLM and Z.ai, Harvey, Vals AI and Artificial Analysis are trademarks of their respective owners. They are named for identification only and this implies no partnership, sponsorship or endorsement.