AIIQ Composite IQ — leaderboard
AIIQ composite estimate that combines abstract, mathematical, programmatic, and academic reasoning benchmark evidence into IQ-like model scores.
Metric: Composite IQ (self-reported). Source: benchmarklist.com. Status: saturated. 47 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 136 |
| 2 | GPT-5.4 | 134 |
| 3 | Gemini 3.1 Pro (Preview) | 132 |
| 4 | Claude Opus 4.7 | 132 |
| 5 | Claude Opus 4.6 | 131 |
| 6 | GPT-5.2 | 126 |
| 7 | Grok 4.3 | 125 |
| 8 | Grok 4.20 | 123 |
| 9 | Claude Opus 4.5 | 123 |
| 10 | GPT-5.1 | 120 |
| 11 | GPT-5 | 119 |
| 12 | DeepSeek V4 Pro | 117 |
| 13 | Muse Spark | 117 |
| 14 | GLM-5.1 | 115 |
| 15 | MiniMax-M2.7 | 114 |
Interactive version: theaggregate.ai/benchmark?slug=aiiq-composite-iq · How the rankings work · Data refreshed daily, snapshot 2026-07-22.