Noometry

Model comparison

GPT-5.2 Pro vs Qwen2.5-Max

GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 40.7 on the Noometry Index.

Last verified . 1 shared benchmarks.

GPT-5.2 Pro OpenAI

52.3

Rank #39 Reported

Qwen2.5-Max Alibaba (Qwen)

40.7

Rank #146 Confirmed

Summary

  • They share 1 benchmark with published results for both. GPT-5.2 Pro scores higher in 2 categories and Qwen2.5-Max in 0 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.2 Pro leads 65.3 to 36.9.

Side by side

GPT-5.2 ProQwen2.5-Max
ProviderOpenAIAlibaba (Qwen)
Noometry Index52.340.7
Released2025-12-112025-01-25
WeightsProprietaryProprietary
Context window400K—
Max output128K—
Input $ / M tokens$21—
Output $ / M tokens$168—
Results tracked827

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

Category by category

Coding Not comparable

GPT-5.2 Pro: —, Qwen2.5-Max: 41.8 (#117)

BenchmarkGPT-5.2 ProQwen2.5-Max
LiveBench Coding—64.4%
LMArena Coding—1359

Reasoning GPT-5.2 Pro leads

GPT-5.2 Pro: 51.5 (#33), Qwen2.5-Max: 25.6 (#147)

BenchmarkGPT-5.2 ProQwen2.5-Max
Epoch Capabilities Index155.4132.53
ARC-AGI-254.2%—
SimpleBench57.4%—
NYT Connections (extended)79.3%—
ARC-AGI-190.5%—
LiveBench Reasoning—51.4%
LMArena Hard Prompts—1360
LiveBench Data Analysis—67.9%
LiveBench—62.3%

Math GPT-5.2 Pro leads

GPT-5.2 Pro: 65.3 (#29), Qwen2.5-Max: 36.9 (#162)

BenchmarkGPT-5.2 ProQwen2.5-Max
FrontierMath (Tiers 1-3)74%—
FrontierMath Tier 446%—
LiveBench Math—58.4%
LMArena Math—1369
FrontierMath Tier 4 (v1)31.3%—

Knowledge Not comparable

GPT-5.2 Pro: —, Qwen2.5-Max: 35.3 (#186)

BenchmarkGPT-5.2 ProQwen2.5-Max
Confabulations—21.8%
LMArena Expert—1337

Multilingual Not comparable

GPT-5.2 Pro: —, Qwen2.5-Max: 48.1 (#146)

BenchmarkGPT-5.2 ProQwen2.5-Max
LMArena Non-English—1352
LMArena Chinese—1382
LMArena French—1396
LMArena German—1350
LMArena Japanese—1300
LMArena Korean—1304
LMArena Russian—1353
LMArena Spanish—1377

Instruction Following Not comparable

GPT-5.2 Pro: —, Qwen2.5-Max: 71.3 (#152)

BenchmarkGPT-5.2 ProQwen2.5-Max
LiveBench Instruction Following—75.3%
LMArena Instruction Following—1335

Long Context Not comparable

GPT-5.2 Pro: —, Qwen2.5-Max: 41.4 (#142)

BenchmarkGPT-5.2 ProQwen2.5-Max
LMArena Longer Query—1358

Writing & Preference Not comparable

GPT-5.2 Pro: —, Qwen2.5-Max: 55.4 (#146)

BenchmarkGPT-5.2 ProQwen2.5-Max
LMArena Text—1367
LMArena Creative Writing—1339
Short-Story Creative Writing—72.9%
LMArena Multi-Turn—1364
LiveBench Language—56.3%

Frequently asked questions

Is GPT-5.2 Pro better than Qwen2.5-Max?

GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 40.7 on the Noometry Index.

How many benchmarks do GPT-5.2 Pro and Qwen2.5-Max share?

1 benchmark has published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Qwen2.5-Max has 27.

Related comparisons

Go deeper