Other · model
Phi-4 Multimodal Instruct benchmark scores
As of 2026-10-07, Phi-4 Multimodal Instruct (Other) has measured scores on 4 benchmarks and estimated scores on 38 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 31.5% | measured |
| AA-HLE | 5.0% | measured |
| Artificial Analysis Intelligence Index | 5.8% | measured |
| CritPt | 0.3% | estimated ± 2.3 pp, high confidence |
| GPQA Diamond | 69.6% | estimated ± 2.2 pp, high confidence |
| HLE | 19.4% | estimated ± 9.9 pp, low confidence |
| AA-Omniscience Accuracy | 17.5% | estimated ± 6.9 pp, medium confidence |
| AA-MMMU-Pro | 14.5% | measured |
| BioMysteryBench (human-difficult) | 35.2% | estimated ± 8.1 pp, low confidence |
| MMLU-Pro | 62.0% | estimated ± 3.9 pp, medium confidence |
| GPQA | 34.4% | estimated ± 3.2 pp, medium confidence |
| ARC-AGI-1 | 0.1% | estimated ± 5.4 pp, low confidence |
| ARC-AGI-2 | 0.1% | estimated ± 14.2 pp, low confidence |
| OfficeQA Pro | 50.3% | estimated ± 7.2 pp, low confidence |
| Vals GPQA Diamond | 20.3% | estimated ± 7.4 pp, low confidence |
| Vals MMLU-Pro | 83.1% | estimated ± 2.5 pp, medium confidence |
| HLE w/o tools | 3.9% | estimated ± 5.7 pp, low confidence |
| CharXiv | 70.3% | estimated ± 7.5 pp, low confidence |
| CharXiv w/o tools | 22.7% | estimated ± 2.4 pp, medium confidence |
| C-Eval | 74.3% | estimated ± 1.0 pp, low confidence |
| MathVision | 81.5% | estimated ± 4.9 pp, medium confidence |
| MMLU-Redux | 70.5% | estimated ± 2.1 pp, low confidence |
| MMMU-Pro | 43.3% | estimated ± 4.4 pp, low confidence |
| ScreenSpot Pro | 55.6% | estimated ± 10.7 pp, low confidence |
| SuperGPQA | 29.8% | estimated ± 10.4 pp, low confidence |
| ERQA | 0.0% | estimated ± 3.9 pp, medium confidence |
| HealthBench Hard | 0.0% | estimated ± 7.7 pp, low confidence |
| MedXpertQA (MM) | 0.0% | estimated ± 6.5 pp, low confidence |
| MMLU-Pro (Arcee) | 76.8% | estimated ± 5.4 pp, low confidence |
| ARC-AGI-3 | 1.6% | estimated ± 10.7 pp, low confidence |
| BioMysteryBench (human-solvable) | 0.0% | estimated ± 1.0 pp, low confidence |
| HealthBench (raw) | 7.8% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 57.7% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 22.0% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 17.6% | estimated ± 1.8 pp, low confidence |
| MMMU | 68.3% | estimated ± 0.9 pp, medium confidence |
| MMLU | 74.6% | estimated ± 1.9 pp, low confidence |
| MMMU-Pro w/ Python | 22.3% | estimated ± 1.6 pp, medium confidence |
| RealWorldQA | 28.0% | estimated ± 1.2 pp, low confidence |
| OmniDocBench 1.5 | 0.0% | estimated ± 6.4 pp, low confidence |