Noometry

Model comparison

GPT-5.4 mini vs Qwen3 Max

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 43.5 on the Noometry Index.

Last verified . 29 shared benchmarks.

GPT-5.4 mini OpenAI

44.8

Rank #69 Confirmed

Qwen3 Max Alibaba (Qwen)

43.5

Rank #82 Confirmed

Summary

  • They share 29 benchmarks with published results for both. GPT-5.4 mini scores higher in 6 categories and Qwen3 Max in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-5.4 mini leads 30.3 to 22.0.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 37.9% for GPT-5.4 mini and 72.5% for Qwen3 Max.
  • GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
  • GPT-5.4 mini accepts more context: 400K tokens versus 262K.

Side by side

GPT-5.4 miniQwen3 Max
ProviderOpenAIAlibaba (Qwen)
Noometry Index44.843.5
Released2026-03-172025-09-23
WeightsProprietaryProprietary
Context window400K262K
Max output128K66K
Input $ / M tokens$0.75$1.20
Output $ / M tokens$4.50$6
Results tracked4633

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: 45.0 (#67), Qwen3 Max: 42.4 (#93)

BenchmarkGPT-5.4 miniQwen3 Max
LMArena Coding14381456
ALE-Bench1,189370.45
FrontierCode27%—
LMArena WebDev1397—
SciCode49.9%—
WeirdML60.3%—

Agentic & Tool Use Not comparable

GPT-5.4 mini: 29.6 (#74), Qwen3 Max: —

BenchmarkGPT-5.4 miniQwen3 Max
DeepResearch Bench36.3%—
Vending-Bench 2—71.56

Reasoning GPT-5.4 mini leads

GPT-5.4 mini: 30.3 (#77), Qwen3 Max: 22.0 (#186)

BenchmarkGPT-5.4 miniQwen3 Max
Kagi LLM Benchmark37.9%72.5%
NYT Connections (extended)61.8%30.1%
Chess Puzzles24%4%
LMArena Hard Prompts14241448
Mystery Game Puzzles11%5%
DTBench80%82.1%
LMCA40.8%28.3%
Epoch Capabilities Index148.83142.41
ARC-AGI-218.9%—
ARC-AGI-163.7%—
CritPt10%—
Thematic Generalization61.7%—
ForecastBench57—

Math GPT-5.4 mini leads

GPT-5.4 mini: 45.4 (#63), Qwen3 Max: 37.6 (#94)

BenchmarkGPT-5.4 miniQwen3 Max
FrontierMath (Tiers 1-3)51.2%18.9%
OTIS Mock AIME 2024-202588.9%73.3%
LMArena Math14181447
FrontierMath Tier 49.8%—
ProofBench21%—
MATH Level 5—97.1%
FrontierMath (Feb 2025 set)28.3%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge GPT-5.4 mini leads

GPT-5.4 mini: 51.4 (#62), Qwen3 Max: 48.1 (#72)

BenchmarkGPT-5.4 miniQwen3 Max
GPQA Diamond86.9%72.6%
SimpleQA Verified29.4%48.7%
LMArena Expert14341457
Vectara Hallucination Rate5.5%—

Multimodal Not comparable

GPT-5.4 mini: 39.0 (#51), Qwen3 Max: —

BenchmarkGPT-5.4 miniQwen3 Max
LMArena Vision1245—

Multilingual Qwen3 Max leads

GPT-5.4 mini: 52.1 (#94), Qwen3 Max: 53.9 (#58)

BenchmarkGPT-5.4 miniQwen3 Max
LMArena Non-English14051429
LMArena Chinese14461479
LMArena French14401450
LMArena German14071463
LMArena Japanese13751399
LMArena Korean13691397
LMArena Russian14171428
LMArena Spanish14031463

Instruction Following Too close to call

GPT-5.4 mini: 74.3 (#99), Qwen3 Max: 75.0 (#81)

BenchmarkGPT-5.4 miniQwen3 Max
LMArena Instruction Following14051420

Long Context GPT-5.4 mini leads

GPT-5.4 mini: 42.9 (#107), Qwen3 Max: 41.6 (#129)

BenchmarkGPT-5.4 miniQwen3 Max
LMArena Longer Query14071439
Fiction.LiveBench—66.7%
CL-bench—14.5%

Writing & Preference GPT-5.4 mini leads

GPT-5.4 mini: 64.2 (#56), Qwen3 Max: 62.6 (#72)

BenchmarkGPT-5.4 miniQwen3 Max
LMArena Text14111439
LMArena Creative Writing13701401
LMArena Multi-Turn14291446
EQ-Bench Creative Writing1665—

Frequently asked questions

Is GPT-5.4 mini better than Qwen3 Max?

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 43.5 on the Noometry Index.

Which is cheaper, GPT-5.4 mini or Qwen3 Max?

GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; Qwen3 Max lists at $1.20 and $6.

Is GPT-5.4 mini or Qwen3 Max better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

GPT-5.4 mini does, with 400K tokens against 262K.

How many benchmarks do GPT-5.4 mini and Qwen3 Max share?

29 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Qwen3 Max has 33.

Related comparisons

Go deeper