# SimpleVQA → MLVU (M-Avg)

Calibration · https://benchgap.net/calibration/1431 · data retrieved 2026-10-29

MLVU (M-Avg) is estimated from SimpleVQA with a Michaelis–Menten curve fitted on 10 models measured on both: y = 1.0506·x / (0.15104 + x), R² = 0.65, cross-validated error 5.0 pp. It is used for 2 estimates.

| Estimated model | SimpleVQA | MLVU (M-Avg) | Source |
|---|---|---|---|
| [Step 3.7 Flash](https://benchgap.net/model/step-3-7-flash.md) | 79.2% | 88.2% | estimated ± 5.0 pp, high confidence |
| [Muse Spark Open](https://benchgap.net/model/muse-spark-open.md) | 73.6% | 87.2% | estimated ± 5.0 pp, high confidence |

## Fitted on

| Model | SimpleVQA | MLVU (M-Avg) |
|---|---|---|
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 65.7% | 81.7% |
| [Gemini 3 Pro](https://benchgap.net/model/gemini-3-pro.md) | 73.2% | 83.0% |
| [GPT-5.2](https://benchgap.net/model/gpt-5-2.md) | 55.8% | 85.6% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 71.2% | 85.0% |
| [LFM3-VL-2B](https://benchgap.net/model/lfm3-vl-2b.md) | 36.3% | 71.3% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 67.1% | 86.7% |
| [Qwen3.6-27B](https://benchgap.net/model/qwen3-6-27b.md) | 56.1% | 86.6% |
| [Qwen3.6-35B-A3B](https://benchgap.net/model/qwen3-6-35b-a3b.md) | 58.9% | 86.2% |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 81.7% | 87.4% |
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 75.0% | 90.8% |