Noometry

Model comparison

GPT-5.5 Pro vs Phi-3.5-mini

GPT-5.5 Pro has enough public results to be ranked (#8); Phi-3.5-mini does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

GPT-5.5 Pro OpenAI

64.3

Rank #8 Confirmed

Phi-3.5-mini Microsoft

36.9

Unranked Sparse

Summary

  • Phi-3.5-mini has downloadable open weights; the other is API-only.

Side by side

GPT-5.5 ProPhi-3.5-mini
ProviderOpenAIMicrosoft
Noometry Index64.336.9
Released2026-04-232024-08-16
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$30—
Output $ / M tokens$180—
Results tracked145

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

Category by category

Coding Not comparable

GPT-5.5 Pro: —, Phi-3.5-mini: 34.6 (#232)

BenchmarkGPT-5.5 ProPhi-3.5-mini
BigCodeBench Instruct—32.8%
BigCodeBench Complete—38.5%

Reasoning Not comparable

GPT-5.5 Pro: 73.3 (#10), Phi-3.5-mini: —

BenchmarkGPT-5.5 ProPhi-3.5-mini
ARC-AGI-284.6%—
SimpleBench76.9%—
ARC-AGI-196.5%—
CritPt30.6%—
Chess Puzzles64%—
DTBench96%—
LMCA53.9%—
Epoch Capabilities Index162.07—
PIQA—81%

Math Not comparable

GPT-5.5 Pro: 84.0 (#10), Phi-3.5-mini: —

BenchmarkGPT-5.5 ProPhi-3.5-mini
FrontierMath (Tiers 1-3)87.7%—
FrontierMath Tier 478%—
OTIS Mock AIME 2024-2025100%—
FrontierMath (Feb 2025 set)52.4%—
FrontierMath Tier 4 (v1)39.6%—
GSM8K—86.2%

Knowledge Not comparable

GPT-5.5 Pro: 64.1 (#19), Phi-3.5-mini: —

BenchmarkGPT-5.5 ProPhi-3.5-mini
GPQA Diamond93.9%—
BoolQ—78%

Frequently asked questions

Is GPT-5.5 Pro better than Phi-3.5-mini?

GPT-5.5 Pro has enough public results to be ranked (#8); Phi-3.5-mini does not yet, so treat this comparison as directional.

How many benchmarks do GPT-5.5 Pro and Phi-3.5-mini share?

0 benchmarks have published results for both models. GPT-5.5 Pro has 14 scored results on Noometry and Phi-3.5-mini has 5.

Related comparisons

Go deeper