Benchmark
TrackingAI IQ (Mensa Norway)
Higher scores are better.
- Models measured
- 38
- Scores recorded
- 64
- Sources
- 1
- IQ weight
- 1.35
Score distribution
- 107.1
- Mean
- 109
- Median
- 27.8
- Std dev
- 67
- 10th percentile
- 142
- 90th percentile
- 52
- Min
This benchmark has a weight of 1.35 for chat models, measured over 38 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 51 | Llama 4 Maverickvision· Tracking AI data | 82 |
| 52 | O3 Provision· Tracking AI data | 82 |
| 53 | GPT 4overbal· Tracking AI data | 79 |
| 54 | GPT-4 Turbo· Tracking AI data | 79 |
| 55 | GPT-5.5 Pro· Tracking AI data | 73 |
| 56 | OpenAI o3vision· Tracking AI data | 73 |
| 57 | Grok 3vision, think· Tracking AI data | 70 |
| 58 | Aihubmix Llama 3.2 90B Visionvision· Tracking AI data | 67 |
| 59 | Claude Opus 4.8vision, max thinking· Tracking AI data | 67 |
| 60 | Claude Opus 4.8vision, extended thinking· Tracking AI data | 61 |
| 61 | GPT 4ovision· Tracking AI data | 58 |
| 62 | O1 Provision· Tracking AI data | 58 |
| 63 | Claude 3 Opusvision· Tracking AI data | 52 |
| 64 | o4 Minivision· Tracking AI data | 52 |
Showing 51–64 of 64 results.