# Phi-4 Multimodal Instruct benchmark scores

Other · model · https://benchgap.net/model/phi-4-multimodal-instruct · data retrieved 2026-11-22

As of 2026-11-22, Phi-4 Multimodal Instruct (Other) has measured scores on 3 benchmarks and estimated scores on 21 more.

| Benchmark | Score | Source |
|---|---|---|
| [AA-GPQA Diamond](https://benchgap.net/b/aa-gpqa-diamond/current.md) | 31.5% | measured |
| [AA-HLE](https://benchgap.net/b/aa-hle/current.md) | 5.0% | measured |
| [Artificial Analysis Intelligence Index](https://benchgap.net/b/artificialanalysis/current.md) | 10.0% | estimated ± 7.4 pp, medium confidence |
| [CritPt](https://benchgap.net/b/critpt/current.md) | 0.2% | estimated ± 3.4 pp, high confidence |
| [GPQA Diamond](https://benchgap.net/b/gpqa-diamond/current.md) | 69.4% | estimated ± 2.4 pp, high confidence |
| [HLE](https://benchgap.net/b/hle/current.md) | 16.9% | estimated ± 8.5 pp, medium confidence |
| [AA-Omniscience Accuracy](https://benchgap.net/b/omniscienceaccuracy/current.md) | 18.5% | estimated ± 7.7 pp, low confidence |
| [AA-MMMU-Pro](https://benchgap.net/b/aa-mmmu-pro/current.md) | 14.5% | measured |
| [MMLU-Pro](https://benchgap.net/b/mmlu-pro/current.md) | 42.2% | estimated ± 7.0 pp, medium confidence |
| [GPQA](https://benchgap.net/b/gpqa/current.md) | 37.6% | estimated ± 6.1 pp, medium confidence |
| [MMLU](https://benchgap.net/b/mmlu/current.md) | 67.3% | estimated ± 8.3 pp, medium confidence |
| [Vals GPQA Diamond](https://benchgap.net/b/vals-gpqa-diamond/current.md) | 30.7% | estimated ± 3.2 pp, medium confidence |
| [Vals MMLU-Pro](https://benchgap.net/b/vals-mmlu-pro/current.md) | 53.8% | estimated ± 3.0 pp, medium confidence |
| [MMMLU](https://benchgap.net/b/mmmlu/current.md) | 66.2% | estimated ± 1.7 pp, medium confidence |
| [AA MMLU-Pro](https://benchgap.net/b/aa-mmlu-pro/current.md) | 85.7% | estimated ± 1.3 pp, medium confidence |
| [ARC-AGI-1](https://benchgap.net/b/arcagi1/current.md) | 61.2% | estimated ± 8.1 pp, low confidence |
| [ARC-AGI-2](https://benchgap.net/b/arc-agi-2/current.md) | 26.1% | estimated ± 14.4 pp, low confidence |
| [HLE w/o tools](https://benchgap.net/b/hlenotools/current.md) | 3.4% | estimated ± 5.4 pp, low confidence |
| [ARC-AGI-3](https://benchgap.net/b/arcagi3/current.md) | 1.3% | estimated ± 9.8 pp, low confidence |
| [ARC-AGI-3 Provider Adapter](https://benchgap.net/b/arc-agi-3-provider-adapter/current.md) | 2.7% | estimated ± 7.3 pp, low confidence |
| [C-Eval](https://benchgap.net/b/ceval/current.md) | 87.8% | estimated ± 1.2 pp, low confidence |
| [MMLU-Redux](https://benchgap.net/b/mmluredux/current.md) | 84.5% | estimated ± 3.3 pp, medium confidence |
| [MMMU-Pro](https://benchgap.net/b/mmmu-pro/current.md) | 18.8% | estimated ± 1.5 pp, medium confidence |
| [SimpleQA](https://benchgap.net/b/simpleqa/current.md) | 4.1% | estimated ± 7.8 pp, low confidence |
