# MMLU → AA-Omniscience Accuracy

Calibration · https://benchgap.net/calibration/mmlu/current/to/omniscienceaccuracy/current · data retrieved 2026-11-18

AA-Omniscience Accuracy is estimated from MMLU with a offset logistic curve fitted on 10 models measured on both: y = 0.1345 + (1.2000 − 0.1345) / (1 + exp(−32.18·(x − 0.9621))), R² = 0.93, cross-validated error 2.4 pp. It is used for 20 estimates.

| Estimated model | MMLU | AA-Omniscience Accuracy | Source |
|---|---|---|---|
| [GPT-4.5](https://benchgap.net/model/gpt-4-5.md) | 90.8% | 29.3% | estimated ± 2.4 pp, high confidence |
| [Sarvam 105B](https://benchgap.net/model/sarvam-105b.md) | 90.6% | 28.5% | estimated ± 2.4 pp, high confidence |
| [Ripple-65B Preview](https://benchgap.net/model/ripple-65b-preview.md) | 89.6% | 24.8% | estimated ± 2.4 pp, high confidence |
| [Grok 2](https://benchgap.net/model/grok-2.md) | 87.5% | 19.5% | estimated ± 2.4 pp, high confidence |
| [Trinity-Large-Preview](https://benchgap.net/model/trinity-large-preview.md) | 87.2% | 19.0% | estimated ± 2.4 pp, high confidence |
| [o3-mini](https://benchgap.net/model/o3-mini.md) | 86.9% | 18.5% | estimated ± 2.4 pp, high confidence |
| [Grok 2 mini](https://benchgap.net/model/grok-2-mini.md) | 86.2% | 17.5% | estimated ± 2.4 pp, high confidence |
| [Particle-1](https://benchgap.net/model/particle-1.md) | 86.1% | 17.4% | estimated ± 2.4 pp, high confidence |
| [Llama 3.1 70B](https://benchgap.net/model/llama-3-1-70b.md) | 86.0% | 17.3% | estimated ± 2.4 pp, high confidence |
| [Llama 3.3 70B](https://benchgap.net/model/llama-3-3-70b.md) | 86.0% | 17.3% | estimated ± 2.4 pp, high confidence |
| [LongCat-Flash-Lite-Sparse](https://benchgap.net/model/longcat-flash-lite-sparse.md) | 85.3% | 16.5% | estimated ± 2.4 pp, high confidence |
| [GPT-OSS 20B](https://benchgap.net/model/gpt-oss-20b.md) | 85.3% | 16.5% | estimated ± 2.4 pp, high confidence |
| [o1-mini](https://benchgap.net/model/o1-mini.md) | 85.2% | 16.4% | estimated ± 2.4 pp, high confidence |
| [Sarvam 30B](https://benchgap.net/model/sarvam-30b.md) | 85.1% | 16.4% | estimated ± 2.4 pp, high confidence |
| [Phi-4](https://benchgap.net/model/phi-4.md) | 84.8% | 16.1% | estimated ± 2.4 pp, high confidence |
| [GPT-4o mini](https://benchgap.net/model/gpt-4o-mini.md) | 82.0% | 14.5% | estimated ± 2.4 pp, high confidence |
| [Mixtral 8x22B Instruct v0.1](https://benchgap.net/model/mixtral-8x22b-instruct-v0-1.md) | 77.8% | 13.7% | estimated ± 2.4 pp, medium confidence |
| [Gemma 2 27B](https://benchgap.net/model/gemma-2-27b.md) | 76.2% | 13.6% | estimated ± 2.4 pp, medium confidence |
| [Llama 3.1 8B](https://benchgap.net/model/llama-3-1-8b.md) | 73.0% | 13.5% | estimated ± 2.4 pp, medium confidence |
| [Phi-3.5-mini](https://benchgap.net/model/phi-3-5-mini.md) | 69.0% | 13.5% | estimated ± 2.4 pp, medium confidence |

## Fitted on

| Model | MMLU | AA-Omniscience Accuracy |
|---|---|---|
| [Claude 3.5 Haiku](https://benchgap.net/model/claude-3-5-haiku.md) | 80.3% | 13.2% |
| [DeepSeek-R1](https://benchgap.net/model/deepseek-r1.md) | 90.8% | 30.5% |
| [GPT-4.1](https://benchgap.net/model/gpt-4-1.md) | 90.2% | 27.8% |
| [GPT-4.1 mini](https://benchgap.net/model/gpt-4-1-mini.md) | 87.5% | 20.3% |
| [GPT-4.1 nano](https://benchgap.net/model/gpt-4-1-nano.md) | 80.1% | 13.7% |
| [GPT-OSS 120B](https://benchgap.net/model/gpt-oss-120b.md) | 90.0% | 21.7% |
| [Kimi K2](https://benchgap.net/model/kimi-k2.md) | 89.5% | 27.4% |
| [Mistral Small 3.1](https://benchgap.net/model/mistral-small-3-1.md) | 80.6% | 15.1% |
| [o1](https://benchgap.net/model/o1.md) | 91.8% | 34.5% |
| [o4-mini](https://benchgap.net/model/o4-mini.md) | 90.0% | 24.8% |
