# SimpleVQA → ERQA

Calibration · https://benchgap.net/calibration/1428 · data retrieved 2026-10-29

ERQA is estimated from SimpleVQA with a linear curve fitted on 12 models measured on both: y = 0.5596·x + 0.2699, R² = 0.52, cross-validated error 7.0 pp. It is used for 0 estimates.

## Fitted on

| Model | SimpleVQA | ERQA |
|---|---|---|
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 65.7% | 46.8% |
| [Gemini 3.1 Pro](https://benchgap.net/model/gemini-3-1-pro.md) | 72.4% | 69.4% |
| [Gemini 3 Pro](https://benchgap.net/model/gemini-3-pro.md) | 73.2% | 70.5% |
| [GPT-5.2](https://benchgap.net/model/gpt-5-2.md) | 55.8% | 59.8% |
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 61.1% | 65.4% |
| [Grok 4.20](https://benchgap.net/model/grok-4-20-beta.md) | 57.4% | 54.1% |
| [LFM3-VL-2B](https://benchgap.net/model/lfm3-vl-2b.md) | 36.3% | 48.2% |
| [Muse Spark](https://benchgap.net/model/muse-spark.md) | 71.3% | 64.7% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 67.1% | 67.5% |
| [Qwen3.6-27B](https://benchgap.net/model/qwen3-6-27b.md) | 56.1% | 62.5% |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 81.7% | 69.8% |
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 75.0% | 77.8% |