# ScreenSpot Pro → ParseBench

Calibration · https://benchgap.net/calibration/1417 · data retrieved 2026-10-29

ParseBench is estimated from ScreenSpot Pro with a Michaelis–Menten + offset curve fitted on 6 models measured on both: y = 0.0127 + 2.0000·x / (1.91088 + x), R² = 0.66, cross-validated error 5.5 pp. It is used for 4 estimates.

| Estimated model | ScreenSpot Pro | ParseBench | Source |
|---|---|---|---|
| [Holo2-235B-A22B](https://benchgap.net/model/holo2-235b-a22b.md) | 70.6% | 55.2% | estimated ± 5.5 pp, low confidence |
| [Holo2-30B-A3B](https://benchgap.net/model/holo2-30b-a3b.md) | 66.1% | 52.7% | estimated ± 5.5 pp, low confidence |
| [Holo2-8B](https://benchgap.net/model/holo2-8b.md) | 58.9% | 48.4% | estimated ± 5.5 pp, low confidence |
| [Holo2-4B](https://benchgap.net/model/holo2-4b.md) | 57.2% | 47.3% | estimated ± 5.5 pp, low confidence |

## Fitted on

| Model | ScreenSpot Pro | ParseBench |
|---|---|---|
| [Claude Opus 4.6](https://benchgap.net/model/claude-opus-4-6.md) | 83.1% | 54.1% |
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 87.9% | 62.3% |
| [Gemini 3.1 Pro](https://benchgap.net/model/gemini-3-1-pro.md) | 84.4% | 69.1% |
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 85.4% | 62.2% |
| [GPT-6 Astra](https://benchgap.net/model/gpt-6-astra.md) | 92.7% | 69.9% |
| [Nemotron 3 Nano Omni 30B A3B](https://benchgap.net/model/nemotron-3-nano-omni-30b-a3b.md) | 57.8% | 48.5% |