# Phi-3.5-mini benchmark scores

Other · model · https://benchgap.net/model/phi-3-5-mini · data retrieved 2026-10-29

As of 2026-10-29, Phi-3.5-mini (Other) has measured scores on 5 benchmarks and estimated scores on 10 more.

| Benchmark | Score | Source |
|---|---|---|
| [AA-GPQA Diamond](https://benchgap.net/b/aa-gpqa-diamond/current.md) | 28.1% | estimated ± 6.3 pp, medium confidence |
| [AA-HLE](https://benchgap.net/b/aa-hle/current.md) | 4.1% | estimated ± 5.0 pp, high confidence |
| [CritPt](https://benchgap.net/b/critpt/current.md) | 0.0% | estimated ± 3.4 pp, medium confidence |
| [GPQA Diamond](https://benchgap.net/b/gpqa-diamond/current.md) | 31.0% | estimated ± 1.2 pp, high confidence |
| [MMLU-Pro](https://benchgap.net/b/mmlu-pro/current.md) | 47.4% | measured |
| [Artificial Analysis Intelligence Index](https://benchgap.net/b/artificialanalysis/current.md) | 1.1% | estimated ± 2.1 pp, medium confidence |
| [BBH](https://benchgap.net/b/bbh/current.md) | 69.0% | measured |
| [GPQA](https://benchgap.net/b/gpqa/current.md) | 30.4% | measured |
| [MMLU](https://benchgap.net/b/mmlu/current.md) | 69.0% | measured |
| [AA-Omniscience Accuracy](https://benchgap.net/b/omniscienceaccuracy/current.md) | 12.9% | estimated ± 1.5 pp, medium confidence |
| [MMMLU](https://benchgap.net/b/mmmlu/current.md) | 55.4% | measured |
| [C-Eval](https://benchgap.net/b/ceval/current.md) | 69.6% | estimated ± 1.2 pp, medium confidence |
| [MMLU-Redux](https://benchgap.net/b/mmluredux/current.md) | 69.2% | estimated ± 0.6 pp, medium confidence |
| [SuperGPQA](https://benchgap.net/b/supergpqa/current.md) | 27.1% | estimated ± 12.1 pp, low confidence |
| [SimpleQA](https://benchgap.net/b/simpleqa/current.md) | 0.0% | estimated ± 14.6 pp, low confidence |