Model comparison

GPT-5.2 Pro vs StarCoder 2 3B

GPT-5.2 Pro has enough public results to be ranked (#39); StarCoder 2 3B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

GPT-5.2 Pro OpenAI

52.3

Rank #39 Reported

StarCoder 2 3B NVIDIA

36.3

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both.
  • StarCoder 2 3B has downloadable open weights; the other is API-only.

Side by side

GPT-5.2 Pro and StarCoder 2 3B specifications
GPT-5.2 ProStarCoder 2 3B
ProviderOpenAINVIDIA
Noometry Index52.336.3
Released2025-12-112024-02-22
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$21—
Output $ / M tokens$168—
Results tracked87

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

Category by category

Coding Not comparable

GPT-5.2 Pro: —, StarCoder 2 3B: 33.5

Coding benchmarks
BenchmarkGPT-5.2 ProStarCoder 2 3B
BigCodeBench Complete—21.4%
HumanEval+—27.4%

Reasoning Not comparable

GPT-5.2 Pro: 51.5 (#33), StarCoder 2 3B: —

Reasoning benchmarks
BenchmarkGPT-5.2 ProStarCoder 2 3B
Epoch Capabilities Index155.488.76
ARC-AGI-254.2%—
SimpleBench57.4%—
NYT Connections (extended)79.3%—
ARC-AGI-190.5%—
WinoGrande—57.1%

Math Not comparable

GPT-5.2 Pro: 65.3 (#29), StarCoder 2 3B: —

Math benchmarks
BenchmarkGPT-5.2 ProStarCoder 2 3B
FrontierMath (Tiers 1-3)74%—
FrontierMath Tier 446%—
FrontierMath Tier 4 (v1)31.3%—
GSM8K—21.6%

Knowledge Not comparable

GPT-5.2 Pro: —, StarCoder 2 3B: —

Knowledge benchmarks
BenchmarkGPT-5.2 ProStarCoder 2 3B
ARC (AI2) Challenge—34.2%
MMLU—36.6%

Frequently asked questions

Is GPT-5.2 Pro better than StarCoder 2 3B?

GPT-5.2 Pro has enough public results to be ranked (#39); StarCoder 2 3B does not yet, so treat this comparison as directional.

How many benchmarks do GPT-5.2 Pro and StarCoder 2 3B share?

1 benchmark has published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and StarCoder 2 3B has 7.

Related comparisons

Go deeper