Noometry

Model comparison

GPT-5.4 mini vs Qwen2.5-Max

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 40.7 on the Noometry Index.

Last verified . 18 shared benchmarks.

GPT-5.4 mini OpenAI

45.0

Rank #76 Confirmed

Qwen2.5-Max Alibaba (Qwen)

40.7

Rank #146 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GPT-5.4 mini scores higher in 8 categories and Qwen2.5-Max in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 35.3.

Side by side

GPT-5.4 miniQwen2.5-Max
ProviderOpenAIAlibaba (Qwen)
Noometry Index45.040.7
Released2026-03-172025-01-25
WeightsProprietaryProprietary
Context window400K—
Max output128K—
Input $ / M tokens$0.75—
Output $ / M tokens$4.50—
Results tracked4627

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

Category by category

Coding GPT-5.4 mini leads

GPT-5.4 mini: 45.2 (#72), Qwen2.5-Max: 41.8 (#117)

BenchmarkGPT-5.4 miniQwen2.5-Max
LMArena Coding14381359
FrontierCode27%—
LMArena WebDev1397—
SciCode49.9%—
WeirdML60.3%—
LiveBench Coding—64.4%
ALE-Bench1,189—

Agentic & Tool Use Not comparable

GPT-5.4 mini: 29.9 (#81), Qwen2.5-Max: —

BenchmarkGPT-5.4 miniQwen2.5-Max
DeepResearch Bench36.3%—

Reasoning GPT-5.4 mini leads

GPT-5.4 mini: 30.4 (#85), Qwen2.5-Max: 25.6 (#147)

BenchmarkGPT-5.4 miniQwen2.5-Max
LMArena Hard Prompts14241360
Epoch Capabilities Index148.84132.53
ARC-AGI-218.9%—
Kagi LLM Benchmark37.9%—
NYT Connections (extended)61.8%—
ARC-AGI-163.7%—
CritPt10%—
Chess Puzzles24%—
Thematic Generalization61.7%—
LiveBench Reasoning—51.4%
Mystery Game Puzzles11%—
DTBench80%—
LiveBench Data Analysis—67.9%
LMCA40.8%—
ForecastBench57—
LiveBench—62.3%

Math GPT-5.4 mini leads

GPT-5.4 mini: 45.5 (#75), Qwen2.5-Max: 36.9 (#162)

BenchmarkGPT-5.4 miniQwen2.5-Max
LMArena Math14191369
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 49.8%—
OTIS Mock AIME 2024-202588.9%—
ProofBench21%—
LiveBench Math—58.4%
FrontierMath (Feb 2025 set)28.3%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge GPT-5.4 mini leads

GPT-5.4 mini: 51.5 (#67), Qwen2.5-Max: 35.3 (#186)

BenchmarkGPT-5.4 miniQwen2.5-Max
LMArena Expert14351337
GPQA Diamond86.9%—
SimpleQA Verified29.4%—
Confabulations—21.8%
Vectara Hallucination Rate5.5%—

Multimodal Not comparable

GPT-5.4 mini: 39.7 (#56), Qwen2.5-Max: —

BenchmarkGPT-5.4 miniQwen2.5-Max
LMArena Vision1245—

Multilingual GPT-5.4 mini leads

GPT-5.4 mini: 51.9 (#96), Qwen2.5-Max: 48.1 (#146)

BenchmarkGPT-5.4 miniQwen2.5-Max
LMArena Non-English14051352
LMArena Chinese14461382
LMArena French14401396
LMArena German14091350
LMArena Japanese13741300
LMArena Korean13681304
LMArena Russian14171353
LMArena Spanish14051377

Instruction Following GPT-5.4 mini leads

GPT-5.4 mini: 74.1 (#102), Qwen2.5-Max: 71.3 (#152)

BenchmarkGPT-5.4 miniQwen2.5-Max
LMArena Instruction Following14051335
LiveBench Instruction Following—75.3%

Long Context GPT-5.4 mini leads

GPT-5.4 mini: 43.0 (#112), Qwen2.5-Max: 41.4 (#142)

BenchmarkGPT-5.4 miniQwen2.5-Max
LMArena Longer Query14071358

Writing & Preference GPT-5.4 mini leads

GPT-5.4 mini: 64.0 (#58), Qwen2.5-Max: 55.4 (#146)

BenchmarkGPT-5.4 miniQwen2.5-Max
LMArena Text14121367
LMArena Creative Writing13701339
LMArena Multi-Turn14291364
Short-Story Creative Writing—72.9%
EQ-Bench Creative Writing1665—
LiveBench Language—56.3%

Frequently asked questions

Is GPT-5.4 mini better than Qwen2.5-Max?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 40.7 on the Noometry Index.

Is GPT-5.4 mini or Qwen2.5-Max better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 41.8 in the Noometry coding category.

How many benchmarks do GPT-5.4 mini and Qwen2.5-Max share?

18 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Qwen2.5-Max has 27.

Related comparisons

Go deeper