# RealWorldQA → MMMU-Pro

Calibration · https://benchgap.net/calibration/realworldqa/current/to/mmmu-pro/current · data retrieved 2026-11-18

MMMU-Pro is estimated from RealWorldQA with a Hill curve fitted on 11 models measured on both: y = 0.0000 + (1.2000 − 0.0000)·x^6.00 / (0.77336^6.00 + x^6.00), R² = 0.61, cross-validated error 11.3 pp. It is used for 1 estimate.

| Estimated model | RealWorldQA | MMMU-Pro | Source |
|---|---|---|---|
| [North Micro Vision Instruct](https://benchgap.net/model/north-micro-vision-instruct.md) | 62.2% | 25.6% | estimated ± 11.3 pp, low confidence |

## Fitted on

| Model | RealWorldQA | MMMU-Pro |
|---|---|---|
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 77.0% | 70.6% |
| [Gemini 3 Pro](https://benchgap.net/model/gemini-3-pro.md) | 83.3% | 81.0% |
| [GPT-5.2](https://benchgap.net/model/gpt-5-2.md) | 83.3% | 79.5% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 81.0% | 78.5% |
| [LFM2.5-VL-3B](https://benchgap.net/model/lfm2-5-vl-3b.md) | 73.1% | 30.5% |
| [LFM3-VL-2B](https://benchgap.net/model/lfm3-vl-2b.md) | 79.3% | 45.7% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 83.9% | 79.0% |
| [Qwen3.6-27B](https://benchgap.net/model/qwen3-6-27b.md) | 84.1% | 75.8% |
| [Qwen3.6-35B-A3B](https://benchgap.net/model/qwen3-6-35b-a3b.md) | 85.3% | 75.3% |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 86.9% | 79.0% |
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 88.0% | 82.3% |
