Noometry

Model comparison

GPT-5.2 Codex vs Qwen3.5 27B

GPT-5.2 Codex and Qwen3.5 27B score almost the same on the Noometry Index (42.6 vs 41.9), so choose on price, context window or the category you care about most.

Last verified . 2 shared benchmarks.

GPT-5.2 Codex OpenAI

42.6

Rank #111 Reported

Qwen3.5 27B Alibaba (Qwen)

41.9

Rank #127 Confirmed

Summary

  • They share 2 benchmarks with published results for both. GPT-5.2 Codex scores higher in 1 category and Qwen3.5 27B in 0 categories; one gap is clear of the uncertainty.
  • The widest gap is in coding, where GPT-5.2 Codex leads 45.5 to 38.9.
  • Qwen3.5 27B is cheaper at $0.30 / $2.40 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
  • GPT-5.2 Codex accepts more context: 400K tokens versus 262K.
  • Qwen3.5 27B has downloadable open weights; the other is API-only.

Side by side

GPT-5.2 CodexQwen3.5 27B
ProviderOpenAIAlibaba (Qwen)
Noometry Index42.641.9
Released2025-12-182026-02-23
WeightsProprietaryOpen
Context window400K262K
Max output128K66K
Input $ / M tokens$1.75$0.30
Output $ / M tokens$14$2.40
Results tracked528

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

Category by category

Coding GPT-5.2 Codex leads

GPT-5.2 Codex: 45.5 (#71), Qwen3.5 27B: 38.9 (#168)

BenchmarkGPT-5.2 CodexQwen3.5 27B
LMArena WebDev13391358
ALE-Bench1,300349.45
SWE-bench Verified (bash only)72.8%—
SWE-bench Multilingual66.3%—
WeirdML—39.5%
LMArena Coding—1427

Agentic & Tool Use Not comparable

GPT-5.2 Codex: 41.0 (#22), Qwen3.5 27B: —

BenchmarkGPT-5.2 CodexQwen3.5 27B
Terminal-Bench66.5%—
Vending-Bench 2—201.98

Reasoning Not comparable

GPT-5.2 Codex: —, Qwen3.5 27B: 27.5 (#117)

BenchmarkGPT-5.2 CodexQwen3.5 27B
NYT Connections (extended)—47.9%
Thematic Generalization—45.5%
LMArena Hard Prompts—1414
DTBench—82.4%
LMCA—34%

Math Not comparable

GPT-5.2 Codex: —, Qwen3.5 27B: 38.8 (#127)

BenchmarkGPT-5.2 CodexQwen3.5 27B
MathArena Final-Answer Competitions—56.7%
LMArena Math—1429

Knowledge Not comparable

GPT-5.2 Codex: —, Qwen3.5 27B: 38.0 (#150)

BenchmarkGPT-5.2 CodexQwen3.5 27B
Vectara Hallucination Rate—12.1%
LMArena Expert—1428

Multimodal Not comparable

GPT-5.2 Codex: —, Qwen3.5 27B: 39.4 (#59)

BenchmarkGPT-5.2 CodexQwen3.5 27B
LMArena Vision—1241

Multilingual Not comparable

GPT-5.2 Codex: —, Qwen3.5 27B: 50.8 (#115)

BenchmarkGPT-5.2 CodexQwen3.5 27B
LMArena Non-English—1390
LMArena Chinese—1478
LMArena French—1410
LMArena German—1393
LMArena Japanese—1345
LMArena Korean—1358
LMArena Russian—1390
LMArena Spanish—1407

Instruction Following Not comparable

GPT-5.2 Codex: —, Qwen3.5 27B: 73.5 (#119)

BenchmarkGPT-5.2 CodexQwen3.5 27B
LMArena Instruction Following—1393

Long Context Not comparable

GPT-5.2 Codex: —, Qwen3.5 27B: 43.1 (#106)

BenchmarkGPT-5.2 CodexQwen3.5 27B
LMArena Longer Query—1413

Writing & Preference Not comparable

GPT-5.2 Codex: —, Qwen3.5 27B: 59.3 (#111)

BenchmarkGPT-5.2 CodexQwen3.5 27B
LMArena Text—1409
LMArena Creative Writing—1362
LMArena Multi-Turn—1410

Frequently asked questions

Is GPT-5.2 Codex better than Qwen3.5 27B?

GPT-5.2 Codex and Qwen3.5 27B score almost the same on the Noometry Index (42.6 vs 41.9), so choose on price, context window or the category you care about most.

Which is cheaper, GPT-5.2 Codex or Qwen3.5 27B?

Qwen3.5 27B is cheaper. It lists at $0.30 per million input tokens and $2.40 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.

Is GPT-5.2 Codex or Qwen3.5 27B better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.5 versus 38.9 in the Noometry coding category.

Which has the bigger context window?

GPT-5.2 Codex does, with 400K tokens against 262K.

How many benchmarks do GPT-5.2 Codex and Qwen3.5 27B share?

2 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Qwen3.5 27B has 28.

Related comparisons

Go deeper