Noometry

Model comparison

GPT-5-Codex vs Llama 3.2 90B

GPT-5-Codex is the stronger model overall, scoring 37.9 to 27.5 on the Noometry Index.

Last verified . 0 shared benchmarks.

GPT-5-Codex OpenAI

37.9

Rank #192 Reported

Llama 3.2 90B Meta

27.5

Rank #331 Confirmed

Summary

  • The widest gap is in reasoning, where GPT-5-Codex leads 30.9 to 21.7.
  • Llama 3.2 90B has downloadable open weights; the other is API-only.

Side by side

GPT-5-CodexLlama 3.2 90B
ProviderOpenAIMeta
Noometry Index37.927.5
Released2025-09-152024-09-24
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$1.25—
Output $ / M tokens$10—
Results tracked39

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

Category by category

Coding Not comparable

GPT-5-Codex: 42.4 (#103), Llama 3.2 90B: —

BenchmarkGPT-5-CodexLlama 3.2 90B
WeirdML54.5%—

Agentic & Tool Use GPT-5-Codex leads

GPT-5-Codex: 31.0 (#72), Llama 3.2 90B: 30.0 (#80)

BenchmarkGPT-5-CodexLlama 3.2 90B
Terminal-Bench44.3%—
BALROG—27.3%

Reasoning GPT-5-Codex leads

GPT-5-Codex: 30.9 (#83), Llama 3.2 90B: 21.7 (#217)

BenchmarkGPT-5-CodexLlama 3.2 90B
Kagi LLM Benchmark70.3%—
EnigmaEval—0.4%
Epoch Capabilities Index—125.5

Math Not comparable

GPT-5-Codex: —, Llama 3.2 90B: 11.1 (#308)

BenchmarkGPT-5-CodexLlama 3.2 90B
OTIS Mock AIME 2024-2025—2.6%
MATH Level 5—39.4%

Knowledge Not comparable

GPT-5-Codex: —, Llama 3.2 90B: 21.7 (#274)

BenchmarkGPT-5-CodexLlama 3.2 90B
GPQA Diamond—41%
MMLU—80.3%

Multimodal Not comparable

GPT-5-Codex: —, Llama 3.2 90B: 25.4 (#124)

BenchmarkGPT-5-CodexLlama 3.2 90B
LMArena Vision—1000
GeoBench—52%

Frequently asked questions

Is GPT-5-Codex better than Llama 3.2 90B?

GPT-5-Codex is the stronger model overall, scoring 37.9 to 27.5 on the Noometry Index.

How many benchmarks do GPT-5-Codex and Llama 3.2 90B share?

0 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Llama 3.2 90B has 9.

Related comparisons

Go deeper