benchgap
Other · model

Phi-4 benchmark scores

As of 2026-11-21, Phi-4 (Other) has measured scores on 9 benchmarks and estimated scores on 30 more.

BenchmarkScoreSource
AA-GPQA Diamond57.5%measured
AA-HLE3.8%measured
Artificial Analysis Intelligence Index9.6%estimated ± 3.2 pp, medium confidence
CritPt0.0%measured
GDPval-AA0.0%estimated ± 11.0 pp, low confidence
GPQA Diamond56.5%estimated ± 1.2 pp, high confidence
HLE3.7%estimated ± 6.5 pp, low confidence
IFBench53.6%estimated ± 6.6 pp, low confidence
AA-LCR0.0%measured
AA-Omniscience Accuracy16.1%estimated ± 2.4 pp, high confidence
BrowseComp0.0%estimated ± 13.0 pp, low confidence
IFEval76.2%estimated ± 2.8 pp, high confidence
LongBench v251.2%estimated ± 5.5 pp, low confidence
τ²-bench results0.0%measured
BioMysteryBench (human-difficult)0.0%estimated ± 6.8 pp, low confidence
AA Agentic Index0.0%estimated ± 12.7 pp, low confidence
MMLU-Pro71.4%estimated ± 4.0 pp, high confidence
AA-IFBench23.5%measured
BBH89.6%estimated ± 2.4 pp, low confidence
GPQA56.1%measured
MMLU84.8%measured
Vals GPQA Diamond56.6%estimated ± 3.2 pp, high confidence
Vals MMLU-Pro71.9%estimated ± 2.3 pp, high confidence
MMMLU83.3%estimated ± 0.7 pp, medium confidence
AA MMLU-Pro83.9%estimated ± 1.2 pp, low confidence
ARC-AGI-174.7%estimated ± 7.8 pp, low confidence
ARC-AGI-230.5%estimated ± 14.4 pp, low confidence
HLE w/o tools11.3%estimated ± 5.3 pp, low confidence
ARC-AGI-31.3%estimated ± 9.8 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
C-Eval90.8%estimated ± 1.1 pp, low confidence
MMLU-ProX49.9%measured
MMLU-Redux86.2%estimated ± 1.7 pp, high confidence
HealthBench Hard0.0%estimated ± 8.6 pp, low confidence
MMLU-Pro (Arcee)77.1%estimated ± 4.0 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
SimpleQA17.2%estimated ± 7.8 pp, medium confidence
MRCRv222.8%estimated ± 11.3 pp, low confidence
BioBasicsBench33.9%estimated ± 10.7 pp, low confidence