# MMMU-Pro → PerceptionBench

Calibration · https://benchgap.net/calibration/mmmu-pro/current/to/perceptionbench/current · data retrieved 2026-11-18

PerceptionBench is estimated from MMMU-Pro with a linear curve fitted on 5 models measured on both: y = 2.9882·x + -1.8258, R² = 0.85, cross-validated error 2.6 pp. It is used for 34 estimates.

| Estimated model | MMMU-Pro | PerceptionBench | Source |
|---|---|---|---|
| [GPT-6.1 Terra](https://benchgap.net/model/gpt-6-1-terra.md) | 85.5% | 72.9% | estimated ± 2.6 pp, low confidence |
| [Gemini 3.1 Pro](https://benchgap.net/model/gemini-3-1-pro.md) | 83.9% | 68.1% | estimated ± 2.6 pp, medium confidence |
| [Gemini 3.5 Flash](https://benchgap.net/model/gemini-3-5-flash.md) | 83.6% | 67.2% | estimated ± 2.6 pp, medium confidence |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 83.0% | 65.4% | estimated ± 2.6 pp, medium confidence |
| [Seed 2.1 Pro](https://benchgap.net/model/seed-2-1-pro.md) | 81.6% | 61.3% | estimated ± 2.6 pp, medium confidence |
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 81.2% | 60.1% | estimated ± 2.6 pp, medium confidence |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 81.2% | 60.1% | estimated ± 2.6 pp, medium confidence |
| [Gemini 3 Pro](https://benchgap.net/model/gemini-3-pro.md) | 81.0% | 59.5% | estimated ± 2.6 pp, medium confidence |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 80.7% | 58.6% | estimated ± 2.6 pp, medium confidence |
| [Muse Spark](https://benchgap.net/model/muse-spark.md) | 80.4% | 57.7% | estimated ± 2.6 pp, medium confidence |
| [Seed 2.1 Turbo](https://benchgap.net/model/seed-2-1-turbo.md) | 80.1% | 56.8% | estimated ± 2.6 pp, medium confidence |
| [GPT-5.2](https://benchgap.net/model/gpt-5-2.md) | 79.5% | 55.0% | estimated ± 2.6 pp, medium confidence |
| [Kimi K2.6](https://benchgap.net/model/kimi-2-6.md) | 79.4% | 54.7% | estimated ± 2.6 pp, medium confidence |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 79.0% | 53.5% | estimated ± 2.6 pp, low confidence |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 79.0% | 53.5% | estimated ± 2.6 pp, low confidence |
| [Qwen3.6 Plus](https://benchgap.net/model/qwen3-6-plus.md) | 78.8% | 52.9% | estimated ± 2.6 pp, low confidence |
| [Hy4](https://benchgap.net/model/hy4.md) | 78.6% | 52.3% | estimated ± 2.6 pp, low confidence |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 78.5% | 52.0% | estimated ± 2.6 pp, low confidence |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 78.4% | 51.7% | estimated ± 2.6 pp, low confidence |
| [Grok 4.3](https://benchgap.net/model/grok-4-3.md) | 78.1% | 50.8% | estimated ± 2.6 pp, low confidence |
| [MiniMax M3](https://benchgap.net/model/minimax-m3.md) | 78.1% | 50.8% | estimated ± 2.6 pp, low confidence |
| [Pareto 26.9](https://benchgap.net/model/pareto-26-9.md) | 78.0% | 50.5% | estimated ± 2.6 pp, low confidence |
| [MiMo-V2.5](https://benchgap.net/model/mimo-v2-5.md) | 77.9% | 50.2% | estimated ± 2.6 pp, low confidence |
| [Claude Opus 4.6](https://benchgap.net/model/claude-opus-4-6.md) | 77.3% | 48.4% | estimated ± 2.6 pp, low confidence |
| [Gemma 4 31B](https://benchgap.net/model/gemma-4-31b.md) | 76.9% | 47.2% | estimated ± 2.6 pp, low confidence |
| [Qwen3.5-122B-A10B](https://benchgap.net/model/qwen3-5-122b-a10b.md) | 76.9% | 47.2% | estimated ± 2.6 pp, low confidence |
| [GPT-5.4 mini](https://benchgap.net/model/gpt-5-4-mini.md) | 76.6% | 46.3% | estimated ± 2.6 pp, low confidence |
| [Step 5 Preview](https://benchgap.net/model/step-5-preview.md) | 76.0% | 44.5% | estimated ± 2.6 pp, low confidence |
| [Hy4 flash](https://benchgap.net/model/hy4-flash.md) | 75.8% | 43.9% | estimated ± 2.6 pp, low confidence |
| [Qwen3.6-27B](https://benchgap.net/model/qwen3-6-27b.md) | 75.8% | 43.9% | estimated ± 2.6 pp, low confidence |
| [Qwen3.6-35B-A3B](https://benchgap.net/model/qwen3-6-35b-a3b.md) | 75.3% | 42.4% | estimated ± 2.6 pp, low confidence |
| [Grok 4.20](https://benchgap.net/model/grok-4-20-beta.md) | 75.2% | 42.1% | estimated ± 2.6 pp, low confidence |
| [Qwen3.5-35B-A3B](https://benchgap.net/model/qwen3-5-35b-a3b.md) | 75.1% | 41.8% | estimated ± 2.6 pp, low confidence |
| [Qwen3.5-27B](https://benchgap.net/model/qwen3-5-27b.md) | 75.0% | 41.5% | estimated ± 2.6 pp, low confidence |

## Fitted on

| Model | MMMU-Pro | PerceptionBench |
|---|---|---|
| [dots3-note Preview](https://benchgap.net/model/dots3-note-preview.md) | 79.1% | 53.4% |
| [Inkling 2 Small](https://benchgap.net/model/inkling-2-small.md) | 81.6% | 64.7% |
| [Kimi K3.1 Pro](https://benchgap.net/model/kimi-3-1-pro.md) | 84.1% | 68.3% |
| [Kimi K3](https://benchgap.net/model/kimi-k3.md) | 81.6% | 58.5% |
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 82.3% | 63.5% |
