# Video-MME (w/o subtitle) → AI2D_TEST

Calibration · https://benchgap.net/calibration/1611 · data retrieved 2026-10-29

AI2D_TEST is estimated from Video-MME (w/o subtitle) with a Michaelis–Menten + offset curve fitted on 7 models measured on both: y = 0.5598 + 2.0000·x / (3.82223 + x), R² = 0.50, cross-validated error 2.5 pp. It is used for 0 estimates.

## Fitted on

| Model | Video-MME (w/o subtitle) | AI2D_TEST |
|---|---|---|
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 81.4% | 87.7% |
| [Gemini 3 Pro](https://benchgap.net/model/gemini-3-pro.md) | 87.7% | 94.1% |
| [GPT-5.2](https://benchgap.net/model/gpt-5-2.md) | 85.8% | 92.2% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 83.2% | 90.8% |
| [Nemotron 3 Nano Omni 30B A3B](https://benchgap.net/model/nemotron-3-nano-omni-30b-a3b.md) | 72.2% | 88.5% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 83.7% | 93.9% |
| [Qwen3.6-35B-A3B](https://benchgap.net/model/qwen3-6-35b-a3b.md) | 82.5% | 92.7% |