# Vals MMLU-Pro → ARC-AGI-2

Calibration · https://benchgap.net/calibration/1556 · data retrieved 2026-10-29

ARC-AGI-2 is estimated from Vals MMLU-Pro with a linear curve fitted on 24 models measured on both: y = 6.0745·x + -4.6954, R² = 0.69, cross-validated error 13.0 pp. It is used for 4 estimates.

| Estimated model | Vals MMLU-Pro | ARC-AGI-2 | Source |
|---|---|---|---|
| [Muse Spark 1.2](https://benchgap.net/model/muse-spark-1-2.md) | 88.3% | 66.8% | estimated ± 13.0 pp, low confidence |
| [Laguna M.1](https://benchgap.net/model/laguna-m-1.md) | 68.8% | 0.0% | estimated ± 13.0 pp, low confidence |
| [Laguna XS.2](https://benchgap.net/model/laguna-xs-2.md) | 69.1% | 0.0% | estimated ± 13.0 pp, low confidence |
| [Mistral Medium 3.5 128B](https://benchgap.net/model/mistral-medium-3-5-128b.md) | 75.3% | 0.0% | estimated ± 13.0 pp, low confidence |

## Fitted on

| Model | Vals MMLU-Pro | ARC-AGI-2 |
|---|---|---|
| [Claude Fable 5](https://benchgap.net/model/claude-fable.md) | 91.5% | 89.2% |
| [Claude Fable 5.1](https://benchgap.net/model/claude-fable-5-1.md) | 92.4% | 90.0% |
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 89.6% | 72.1% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 91.6% | 90.4% |
| [Claude Sonnet 4.6](https://benchgap.net/model/claude-sonnet-4-6.md) | 87.3% | 58.3% |
| [DeepSeek V4 Flash 0731](https://benchgap.net/model/deepseek-v4-flash-0731.md) | 86.2% | 61.4% |
| [DeepSeek V4 Pro 0813](https://benchgap.net/model/deepseek-v4-pro-0813.md) | 87.0% | 61.3% |
| [Gemini 3.1 Pro](https://benchgap.net/model/gemini-3-1-pro.md) | 91.0% | 77.1% |
| [Gemini 3.5 Flash](https://benchgap.net/model/gemini-3-5-flash.md) | 89.5% | 72.1% |
| [Gemini 3.6 Flash](https://benchgap.net/model/gemini-3-6-flash.md) | 89.3% | 60.4% |
| [Gemini 3.7 Flash](https://benchgap.net/model/gemini-3-7-flash.md) | 90.1% | 84.6% |
| [Gemini 3.8 Flash](https://benchgap.net/model/gemini-3-8-flash.md) | 90.2% | 89.2% |
| [GPT-5.4 mini](https://benchgap.net/model/gpt-5-4-mini.md) | 84.6% | 18.9% |
| [GPT-5.4 nano](https://benchgap.net/model/gpt-5-4-nano.md) | 77.2% | 5.7% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 88.1% | 85.0% |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 86.0% | 59.5% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 89.1% | 92.5% |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 86.7% | 83.9% |
| [Grok 4.20](https://benchgap.net/model/grok-4-20-beta.md) | 86.3% | 53.3% |
| [Grok 4.5](https://benchgap.net/model/grok-4-5.md) | 89.2% | 52.6% |
| [Grok 4.6](https://benchgap.net/model/grok-4-6.md) | 89.4% | 67.1% |
| [Inkling-Small](https://benchgap.net/model/inkling-small.md) | 85.6% | 40.1% |
| [Kimi K3](https://benchgap.net/model/kimi-k3.md) | 88.0% | 60.4% |
| [Muse Spark](https://benchgap.net/model/muse-spark.md) | 87.3% | 42.5% |