# Vals MMLU-Pro → AA-Omniscience Accuracy

Calibration · https://benchgap.net/calibration/1567 · data retrieved 2026-10-29

AA-Omniscience Accuracy is estimated from Vals MMLU-Pro with a offset logistic curve fitted on 45 models measured on both: y = 0.2215 + (0.9024 − 0.2215) / (1 + exp(−34.58·(x − 0.9052))), R² = 0.65, cross-validated error 7.7 pp. It is used for 9 estimates.

| Estimated model | Vals MMLU-Pro | AA-Omniscience Accuracy | Source |
|---|---|---|---|
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 88.6% | 45.3% | estimated ± 7.7 pp, medium confidence |
| [Gemini 3.1 Flash-Lite](https://benchgap.net/model/gemini-3-1-flash-lite.md) | 86.2% | 34.6% | estimated ± 7.7 pp, medium confidence |
| [GLM-5.3-Flash](https://benchgap.net/model/glm-5-3-flash.md) | 86.1% | 34.3% | estimated ± 7.7 pp, medium confidence |
| [Qwen3.5 Flash](https://benchgap.net/model/qwen3-5-flash.md) | 84.1% | 28.8% | estimated ± 7.7 pp, medium confidence |
| [MiMo-V2.5](https://benchgap.net/model/mimo-v2-5.md) | 82.9% | 26.7% | estimated ± 7.7 pp, medium confidence |
| [GLM-4.5](https://benchgap.net/model/glm-4-5.md) | 81.2% | 24.8% | estimated ± 7.7 pp, medium confidence |
| [Claude Haiku 4.5](https://benchgap.net/model/claude-haiku-4-5.md) | 78.7% | 23.3% | estimated ± 7.7 pp, medium confidence |
| [Laguna XS.2](https://benchgap.net/model/laguna-xs-2.md) | 69.1% | 22.2% | estimated ± 7.7 pp, low confidence |
| [Laguna M.1](https://benchgap.net/model/laguna-m-1.md) | 68.8% | 22.2% | estimated ± 7.7 pp, low confidence |

## Fitted on

| Model | Vals MMLU-Pro | AA-Omniscience Accuracy |
|---|---|---|
| [Claude Fable 5](https://benchgap.net/model/claude-fable.md) | 91.5% | 65.4% |
| [Claude Fable 5.1](https://benchgap.net/model/claude-fable-5-1.md) | 92.4% | 68.4% |
| [Claude Opus 4.7](https://benchgap.net/model/claude-opus-4-7.md) | 89.9% | 44.7% |
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 89.6% | 48.8% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 91.6% | 60.9% |
| [Claude Sonnet 4.6](https://benchgap.net/model/claude-sonnet-4-6.md) | 87.3% | 38.6% |
| [Claude Sonnet 5](https://benchgap.net/model/claude-sonnet-5.md) | 87.5% | 40.1% |
| [DeepSeek V4 Flash 0731](https://benchgap.net/model/deepseek-v4-flash-0731.md) | 86.2% | 40.4% |
| [DeepSeek V4 Pro 0813](https://benchgap.net/model/deepseek-v4-pro-0813.md) | 87.0% | 49.1% |
| [Gemini 3.5 Flash](https://benchgap.net/model/gemini-3-5-flash.md) | 89.5% | 51.9% |
| [Gemini 3.5 Flash-Lite](https://benchgap.net/model/gemini-3-5-flash-lite.md) | 85.8% | 26.5% |
| [Gemini 3.6 Flash](https://benchgap.net/model/gemini-3-6-flash.md) | 89.3% | 50.0% |
| [Gemini 3.7 Flash](https://benchgap.net/model/gemini-3-7-flash.md) | 90.1% | 55.3% |
| [Gemini 3.8 Flash](https://benchgap.net/model/gemini-3-8-flash.md) | 90.2% | 50.5% |
| [Gemini 3 Flash](https://benchgap.net/model/gemini-3-flash.md) | 88.6% | 45.8% |
| [GLM-4.6](https://benchgap.net/model/glm-4-6.md) | 82.2% | 21.4% |
| [GLM-4.7](https://benchgap.net/model/glm-4-7.md) | 82.7% | 29.3% |
| [GLM-5.1](https://benchgap.net/model/glm-5-1.md) | 86.9% | 23.7% |
| [GLM-5.2](https://benchgap.net/model/glm-5-2.md) | 86.7% | 24.3% |
| [GLM-5.3](https://benchgap.net/model/glm-5-3.md) | 86.8% | 32.3% |
| [GPT-5.4 mini](https://benchgap.net/model/gpt-5-4-mini.md) | 84.6% | 37.5% |
| [GPT-5.4 nano](https://benchgap.net/model/gpt-5-4-nano.md) | 77.2% | 25.7% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 88.1% | 58.0% |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 86.0% | 42.7% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 89.1% | 59.4% |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 86.7% | 46.8% |
| [Grok 4.3](https://benchgap.net/model/grok-4-3.md) | 85.8% | 34.6% |
| [Grok 4.5](https://benchgap.net/model/grok-4-5.md) | 89.2% | 51.6% |
| [Grok 4.6](https://benchgap.net/model/grok-4-6.md) | 89.4% | 48.2% |
| [Inkling](https://benchgap.net/model/inkling.md) | 86.3% | 39.3% |
| [Inkling-Small](https://benchgap.net/model/inkling-small.md) | 85.6% | 31.8% |
| [Kimi K2.6](https://benchgap.net/model/kimi-2-6.md) | 87.6% | 32.6% |
| [Kimi K3](https://benchgap.net/model/kimi-k3.md) | 88.0% | 47.6% |
| [Ling 3.0 Flash](https://benchgap.net/model/ling-3-0-flash.md) | 82.0% | 18.2% |
| [MiMo-V2.5-Pro](https://benchgap.net/model/mimo-v2-5-pro.md) | 84.6% | 22.4% |
| [MiniMax M2.7](https://benchgap.net/model/minimax-m2-7.md) | 80.4% | 26.8% |
| [MiniMax M3](https://benchgap.net/model/minimax-m3.md) | 84.2% | 44.9% |
| [Mistral Medium 3.5 128B](https://benchgap.net/model/mistral-medium-3-5-128b.md) | 75.3% | 23.0% |
| [Muse Spark](https://benchgap.net/model/muse-spark.md) | 87.3% | 49.6% |
| [Muse Spark 1.1](https://benchgap.net/model/muse-spark-1-1.md) | 88.7% | 52.1% |
| [Muse Spark 1.2](https://benchgap.net/model/muse-spark-1-2.md) | 88.3% | 45.4% |
| [Nemotron 3 Ultra](https://benchgap.net/model/nemotron-3-ultra.md) | 85.8% | 21.6% |
| [Qwen3.6 Plus](https://benchgap.net/model/qwen3-6-plus.md) | 87.7% | 26.4% |
| [Qwen3.7 Max](https://benchgap.net/model/qwen3-7-max.md) | 89.3% | 31.1% |
| [Qwen3.8-27B](https://benchgap.net/model/qwen3-8-27b.md) | 84.3% | 17.3% |