Noometry

Model comparison

GPT-5.2 Codex vs Qwen3-1.7B

GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 26.6 on the Noometry Index.

Last verified . 0 shared benchmarks.

GPT-5.2 Codex OpenAI

42.6

Rank #111 Reported

Qwen3-1.7B Alibaba (Qwen)

26.6

Rank #336 Reported

Summary

  • The widest gap is in agentic & tool use, where GPT-5.2 Codex leads 41.0 to 24.7.
  • Qwen3-1.7B has downloadable open weights; the other is API-only.

Side by side

GPT-5.2 CodexQwen3-1.7B
ProviderOpenAIAlibaba (Qwen)
Noometry Index42.626.6
Released2025-12-182025-04-29
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$1.75—
Output $ / M tokens$14—
Results tracked54

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

Category by category

Coding Not comparable

GPT-5.2 Codex: 45.5 (#71), Qwen3-1.7B: —

BenchmarkGPT-5.2 CodexQwen3-1.7B
SWE-bench Verified (bash only)72.8%—
LMArena WebDev1339—
SWE-bench Multilingual66.3%—
ALE-Bench1,300—

Agentic & Tool Use GPT-5.2 Codex leads

GPT-5.2 Codex: 41.0 (#22), Qwen3-1.7B: 24.7 (#115)

BenchmarkGPT-5.2 CodexQwen3-1.7B
Terminal-Bench66.5%—
Berkeley Function Calling Leaderboard—28.4%

Reasoning Not comparable

GPT-5.2 Codex: —, Qwen3-1.7B: 19.2 (#267)

BenchmarkGPT-5.2 CodexQwen3-1.7B
Chess Puzzles—0%

Math Not comparable

GPT-5.2 Codex: —, Qwen3-1.7B: 16.3 (#294)

BenchmarkGPT-5.2 CodexQwen3-1.7B
OTIS Mock AIME 2024-2025—8.1%

Knowledge Not comparable

GPT-5.2 Codex: —, Qwen3-1.7B: 19.6 (#278)

BenchmarkGPT-5.2 CodexQwen3-1.7B
GPQA Diamond—38%

Frequently asked questions

Is GPT-5.2 Codex better than Qwen3-1.7B?

GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 26.6 on the Noometry Index.

How many benchmarks do GPT-5.2 Codex and Qwen3-1.7B share?

0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Qwen3-1.7B has 4.

Related comparisons

Go deeper