Noometry

Model comparison

GPT-5.4 Pro vs phi-3-small 7.4B

GPT-5.4 Pro has enough public results to be ranked (#18); phi-3-small 7.4B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

GPT-5.4 Pro OpenAI

58.9

Rank #18 Confirmed

phi-3-small 7.4B Microsoft

—

Unranked

Summary

  • They share 1 benchmark with published results for both.

Side by side

GPT-5.4 Prophi-3-small 7.4B
ProviderOpenAIMicrosoft
Noometry Index58.9—
Released2026-03-05—
WeightsProprietaryProprietary
Context window1.05M—
Max output128K—
Input $ / M tokens$30—
Output $ / M tokens$180—
Results tracked161

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

GPT-5.4 Pro: 43.2 (#90), phi-3-small 7.4B: —

BenchmarkGPT-5.4 Prophi-3-small 7.4B
WeirdML57.4%—

Reasoning Not comparable

GPT-5.4 Pro: 70.7 (#13), phi-3-small 7.4B: —

BenchmarkGPT-5.4 Prophi-3-small 7.4B
Epoch Capabilities Index158.93121.83
ARC-AGI-283.3%—
SimpleBench74.1%—
ARC-AGI-194.5%—
CritPt30%—
Chess Puzzles58.6%—
EnigmaEval23.8%—

Math Not comparable

GPT-5.4 Pro: 72.4 (#22), phi-3-small 7.4B: —

BenchmarkGPT-5.4 Prophi-3-small 7.4B
FrontierMath (Tiers 1-3)82.5%—
FrontierMath Tier 458.5%—
FrontierMath (Feb 2025 set)50%—
FrontierMath Tier 4 (v1)37.5%—

Knowledge Not comparable

GPT-5.4 Pro: 68.3 (#7), phi-3-small 7.4B: —

BenchmarkGPT-5.4 Prophi-3-small 7.4B
GPQA Diamond94.6%—
Humanity's Last Exam44.3%—
SimpleQA Verified46.3%—
Vectara Hallucination Rate8.3%—

Frequently asked questions

Is GPT-5.4 Pro better than phi-3-small 7.4B?

GPT-5.4 Pro has enough public results to be ranked (#18); phi-3-small 7.4B does not yet, so treat this comparison as directional.

How many benchmarks do GPT-5.4 Pro and phi-3-small 7.4B share?

1 benchmark has published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and phi-3-small 7.4B has 1.

Related comparisons

Go deeper