# MMMU-Pro → OCRBench V2

Calibration · https://benchgap.net/calibration/mmmu-pro/current/to/ocrbenchv2/current · data retrieved 2026-11-19

OCRBench V2 is estimated from MMMU-Pro with a Michaelis–Menten curve fitted on 8 models measured on both: y = 1.0012·x / (0.31797 + x), R² = 0.91, cross-validated error 3.3 pp. It is used for 40 estimates.

| Estimated model | MMMU-Pro | OCRBench V2 | Source |
|---|---|---|---|
| [GPT-6.1 Terra](https://benchgap.net/model/gpt-6-1-terra.md) | 85.5% | 73.0% | estimated ± 3.3 pp, medium confidence |
| [Kimi K3.1 Pro](https://benchgap.net/model/kimi-3-1-pro.md) | 84.1% | 72.7% | estimated ± 3.3 pp, medium confidence |
| [Gemini 3.1 Pro](https://benchgap.net/model/gemini-3-1-pro.md) | 83.9% | 72.6% | estimated ± 3.3 pp, medium confidence |
| [Gemini 3.5 Flash](https://benchgap.net/model/gemini-3-5-flash.md) | 83.6% | 72.5% | estimated ± 3.3 pp, medium confidence |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 83.0% | 72.4% | estimated ± 3.3 pp, medium confidence |
| [Inkling 2 Small](https://benchgap.net/model/inkling-2-small.md) | 81.6% | 72.0% | estimated ± 3.3 pp, high confidence |
| [Kimi K3](https://benchgap.net/model/kimi-k3.md) | 81.6% | 72.0% | estimated ± 3.3 pp, high confidence |
| [Seed 2.1 Pro](https://benchgap.net/model/seed-2-1-pro.md) | 81.6% | 72.0% | estimated ± 3.3 pp, high confidence |
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 81.2% | 71.9% | estimated ± 3.3 pp, high confidence |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 81.2% | 71.9% | estimated ± 3.3 pp, high confidence |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 80.7% | 71.8% | estimated ± 3.3 pp, high confidence |
| [Muse Spark](https://benchgap.net/model/muse-spark.md) | 80.4% | 71.7% | estimated ± 3.3 pp, high confidence |
| [Seed 2.1 Turbo](https://benchgap.net/model/seed-2-1-turbo.md) | 80.1% | 71.7% | estimated ± 3.3 pp, high confidence |
| [Kimi K2.6](https://benchgap.net/model/kimi-2-6.md) | 79.4% | 71.5% | estimated ± 3.3 pp, high confidence |
| [Hy4](https://benchgap.net/model/hy4.md) | 78.6% | 71.3% | estimated ± 3.3 pp, high confidence |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 78.4% | 71.2% | estimated ± 3.3 pp, high confidence |
| [Grok 4.3](https://benchgap.net/model/grok-4-3.md) | 78.1% | 71.2% | estimated ± 3.3 pp, high confidence |
| [Pareto 26.9](https://benchgap.net/model/pareto-26-9.md) | 78.0% | 71.1% | estimated ± 3.3 pp, high confidence |
| [MiMo-V2.5](https://benchgap.net/model/mimo-v2-5.md) | 77.9% | 71.1% | estimated ± 3.3 pp, high confidence |
| [Claude Opus 4.6](https://benchgap.net/model/claude-opus-4-6.md) | 77.3% | 70.9% | estimated ± 3.3 pp, high confidence |
| [Gemma 4 31B](https://benchgap.net/model/gemma-4-31b.md) | 76.9% | 70.8% | estimated ± 3.3 pp, high confidence |
| [Qwen3.5-122B-A10B](https://benchgap.net/model/qwen3-5-122b-a10b.md) | 76.9% | 70.8% | estimated ± 3.3 pp, high confidence |
| [GPT-5.4 mini](https://benchgap.net/model/gpt-5-4-mini.md) | 76.6% | 70.8% | estimated ± 3.3 pp, high confidence |
| [Step 5 Preview](https://benchgap.net/model/step-5-preview.md) | 76.0% | 70.6% | estimated ± 3.3 pp, high confidence |
| [Hy4 flash](https://benchgap.net/model/hy4-flash.md) | 75.8% | 70.5% | estimated ± 3.3 pp, high confidence |
| [Grok 4.20](https://benchgap.net/model/grok-4-20-beta.md) | 75.2% | 70.4% | estimated ± 3.3 pp, high confidence |
| [Qwen3.5-35B-A3B](https://benchgap.net/model/qwen3-5-35b-a3b.md) | 75.1% | 70.3% | estimated ± 3.3 pp, high confidence |
| [Qwen3.5-27B](https://benchgap.net/model/qwen3-5-27b.md) | 75.0% | 70.3% | estimated ± 3.3 pp, high confidence |
| [Inkling-Small](https://benchgap.net/model/inkling-small.md) | 74.0% | 70.0% | estimated ± 3.3 pp, high confidence |
| [Muse Glimmer 30B](https://benchgap.net/model/muse-glimmer-30b.md) | 74.0% | 70.0% | estimated ± 3.3 pp, high confidence |
| [Gemma 4 26B A4B](https://benchgap.net/model/gemma-4-26b-a4b.md) | 73.8% | 70.0% | estimated ± 3.3 pp, high confidence |
| [Inkling](https://benchgap.net/model/inkling.md) | 73.5% | 69.9% | estimated ± 3.3 pp, high confidence |
| [Gemma 4 12B](https://benchgap.net/model/gemma-4-12b.md) | 69.1% | 68.6% | estimated ± 3.3 pp, high confidence |
| [GPT-5.4 nano](https://benchgap.net/model/gpt-5-4-nano.md) | 66.1% | 67.6% | estimated ± 3.3 pp, high confidence |
| [Command A+](https://benchgap.net/model/command-a-plus.md) | 63.0% | 66.5% | estimated ± 3.3 pp, high confidence |
| [MiniMax-VL-01](https://benchgap.net/model/minimax-vl-01.md) | 52.7% | 62.4% | estimated ± 3.3 pp, high confidence |
| [Gemma 4 E4B](https://benchgap.net/model/gemma-4-e4b.md) | 52.6% | 62.4% | estimated ± 3.3 pp, high confidence |
| [Qwen2.5-VL-32B](https://benchgap.net/model/qwen2-5-vl-32b.md) | 49.5% | 61.0% | estimated ± 3.3 pp, high confidence |
| [Mistral Small 3.1](https://benchgap.net/model/mistral-small-3-1.md) | 49.3% | 60.8% | estimated ± 3.3 pp, high confidence |
| [Gemma 4 E2B](https://benchgap.net/model/gemma-4-e2b.md) | 44.2% | 58.2% | estimated ± 3.3 pp, high confidence |

## Fitted on

| Model | MMMU-Pro | OCRBench V2 |
|---|---|---|
| [GLM-4.6V](https://benchgap.net/model/glm-4-6v.md) | 66.0% | 65.1% |
| [GLM-4.6V-Flash](https://benchgap.net/model/glm-4-6v-flash.md) | 60.6% | 63.5% |
| [Interfaze Beta](https://benchgap.net/model/interfaze-beta.md) | 71.1% | 70.7% |
| [LFM2.5-VL-3B](https://benchgap.net/model/lfm2-5-vl-3b.md) | 30.5% | 47.5% |
| [LFM3-VL-2B](https://benchgap.net/model/lfm3-vl-2b.md) | 45.7% | 63.5% |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 79.0% | 70.7% |
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 82.3% | 74.2% |
| [Qwen3-VL-235B-A22B Instruct](https://benchgap.net/model/qwen3-vl-235b-a22b-instruct.md) | 68.1% | 67.1% |
