DiagnosticIQ — leaderboard
Metric: Macro % D.IQ (self-reported). Source: benchmarklist.com. 33 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 73.59 |
| 2 | GPT-5.4 | 73.27 |
| 3 | Gemini 3.1 Pro (Preview) | 72.74 |
| 4 | Claude 3.7 Sonnet | 70.61 |
| 5 | Qwen 3.6 35B A3B | 69.9 |
| 6 | DeepSeek V3 | 67.02 |
| 7 | GPT-5 | 65.89 |
| 8 | O1 | 65.41 |
| 9 | Gemma 4 31B | 65.06 |
| 10 | Claude Sonnet 4.6 | 64.84 |
| 11 | Llama 4 Maverick | 63.29 |
| 12 | Gemma 4 26B | 63.2 |
| 13 | Mistral Large | 63.15 |
| 14 | Claude Sonnet 4 | 62.52 |
| 15 | Gemini 2.0 Flash | 57.64 |
Interactive version: theaggregate.ai/benchmark?slug=diagnosticiq · How the rankings work · Data refreshed daily, snapshot 2026-07-22.