# Video-MME (with subtitle) → RealWorldQA

Calibration · https://benchgap.net/calibration/1633 · data retrieved 2026-10-29

RealWorldQA is estimated from Video-MME (with subtitle) with a offset logistic curve fitted on 10 models measured on both: y = 0.7813 + (0.9386 − 0.7813) / (1 + exp(−30.48·(x − 0.8912))), R² = 0.73, cross-validated error 2.8 pp. It is used for 0 estimates.

## Fitted on

| Model | Video-MME (with subtitle) | RealWorldQA |
|---|---|---|
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 77.6% | 77.0% |
| [Gemini 3 Pro](https://benchgap.net/model/gemini-3-pro.md) | 88.4% | 83.3% |
| [GPT-5.2](https://benchgap.net/model/gpt-5-2.md) | 86.0% | 83.3% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 87.4% | 81.0% |
| [LFM3-VL-2B](https://benchgap.net/model/lfm3-vl-2b.md) | 69.0% | 79.3% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 87.5% | 83.9% |
| [Qwen3.6-27B](https://benchgap.net/model/qwen3-6-27b.md) | 87.7% | 84.1% |
| [Qwen3.6-35B-A3B](https://benchgap.net/model/qwen3-6-35b-a3b.md) | 86.6% | 85.3% |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 88.0% | 86.9% |
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 90.4% | 88.0% |