Model comparison

o1-pro vs phi-3-medium 14B

o1-pro is the stronger model overall, scoring 31.5 to 29.7 on the Noometry Index.

Last verified . 0 shared benchmarks.

o1-pro OpenAI

31.5

Rank #271 Reported

phi-3-medium 14B Microsoft

29.7

Rank #306 Reported

Summary

  • The widest gap is in knowledge, where o1-pro leads 29.7 to 9.1.
  • phi-3-medium 14B has downloadable open weights; the other is API-only.

Side by side

o1-pro and phi-3-medium 14B specifications
o1-prophi-3-medium 14B
ProviderOpenAIMicrosoft
Noometry Index31.529.7
Released2025-03-192024-04-23
WeightsProprietaryOpen
Context window200K—
Max output100K—
Input $ / M tokens$150—
Output $ / M tokens$600—
Results tracked313

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

Category by category

Coding Not comparable

o1-pro: —, phi-3-medium 14B: 36.8 (#201)

Coding benchmarks
Benchmarko1-prophi-3-medium 14B
BigCodeBench Instruct—37.6%
BigCodeBench Complete—48.7%

Reasoning Not comparable

o1-pro: 20.4 (#239), phi-3-medium 14B: —

Reasoning benchmarks
Benchmarko1-prophi-3-medium 14B
ARC-AGI-123.3%—
EnigmaEval6.1%—
Adversarial NLI—55.8%
BIG-Bench Hard—81.4%
Epoch Capabilities Index—121.23
HellaSwag—82.4%
WinoGrande—81.5%

Math Not comparable

o1-pro: —, phi-3-medium 14B: 27.3 (#250)

Math benchmarks
Benchmarko1-prophi-3-medium 14B
MATH Level 5—17.6%

Knowledge o1-pro leads

o1-pro: 29.7 (#234), phi-3-medium 14B: 9.1 (#306)

Knowledge benchmarks
Benchmarko1-prophi-3-medium 14B
GPQA Diamond—27.6%
Humanity's Last Exam8.1%—
ARC (AI2) Challenge—91.6%
MMLU—78%
OpenBookQA—87.4%
TriviaQA—73.9%

Frequently asked questions

Is o1-pro better than phi-3-medium 14B?

o1-pro is the stronger model overall, scoring 31.5 to 29.7 on the Noometry Index.

How many benchmarks do o1-pro and phi-3-medium 14B share?

0 benchmarks have published results for both models. o1-pro has 3 scored results on Noometry and phi-3-medium 14B has 13.

Related comparisons

Go deeper