Noometry

Model comparison

GPT-4 vs Qwen3 Max

Qwen3 Max is the stronger model overall, scoring 43.7 to 29.1 on the Noometry Index.

Last verified . 25 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Qwen3 Max Alibaba (Qwen)

43.7

Rank #87 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Qwen3 Max in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 18.4.
  • The biggest single-benchmark swing is MATH Level 5: 23% for GPT-4 and 97.1% for Qwen3 Max.
  • Qwen3 Max is cheaper at $1.20 / $6 per million input/output tokens, against $30 / $60 for GPT-4.
  • Qwen3 Max accepts more context: 262K tokens versus 8K.

Side by side

GPT-4Qwen3 Max
ProviderOpenAIAlibaba (Qwen)
Noometry Index29.143.7
Released2023-03-142025-09-23
WeightsProprietaryProprietary
Context window8K262K
Max output8K66K
Input $ / M tokens$30$1.20
Output $ / M tokens$60$6
Results tracked3833

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

Category by category

Coding Qwen3 Max leads

GPT-4: 31.6 (#283), Qwen3 Max: 43.0 (#93)

BenchmarkGPT-4Qwen3 Max
LMArena Coding12541456
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
ALE-Bench—370.45
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Qwen3 Max: —

BenchmarkGPT-4Qwen3 Max
METR Time Horizons36.1%—
Vending-Bench 2—71.56

Reasoning Qwen3 Max leads

GPT-4: 17.8 (#289), Qwen3 Max: 22.6 (#190)

BenchmarkGPT-4Qwen3 Max
Chess Puzzles4%4%
LMArena Hard Prompts12411448
Mystery Game Puzzles12%5%
DTBench62.7%82.1%
LMCA17.1%28.3%
Epoch Capabilities Index125.89142.38
Kagi LLM Benchmark—72.5%
NYT Connections (extended)—30.1%
BIG-Bench Hard75.1%—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Qwen3 Max leads

GPT-4: 10.8 (#309), Qwen3 Max: 38.7 (#131)

BenchmarkGPT-4Qwen3 Max
OTIS Mock AIME 2024-20251.1%73.3%
LMArena Math12691446
MATH Level 523%97.1%
FrontierMath (Tiers 1-3)—18.9%
GSM8K92%—

Knowledge Qwen3 Max leads

GPT-4: 18.4 (#282), Qwen3 Max: 48.1 (#78)

BenchmarkGPT-4Qwen3 Max
GPQA Diamond35.7%72.6%
LMArena Expert12111455
SimpleQA Verified—48.7%
MMLU86.4%—
TriviaQA84.8%—

Multilingual Qwen3 Max leads

GPT-4: 40.6 (#215), Qwen3 Max: 53.7 (#62)

BenchmarkGPT-4Qwen3 Max
LMArena Non-English12461429
LMArena Chinese12421478
LMArena French12831449
LMArena German12511463
LMArena Japanese12091397
LMArena Korean11841399
LMArena Russian12511428
LMArena Spanish12611462

Instruction Following Qwen3 Max leads

GPT-4: 65.3 (#222), Qwen3 Max: 74.8 (#87)

BenchmarkGPT-4Qwen3 Max
LMArena Instruction Following12411419

Long Context Qwen3 Max leads

GPT-4: 37.7 (#212), Qwen3 Max: 41.6 (#134)

BenchmarkGPT-4Qwen3 Max
LMArena Longer Query12441438
Fiction.LiveBench—66.7%
CL-bench—14.5%

Writing & Preference Qwen3 Max leads

GPT-4: 34.9 (#268), Qwen3 Max: 62.4 (#76)

BenchmarkGPT-4Qwen3 Max
LMArena Text12631439
LMArena Creative Writing12441402
LMArena Multi-Turn12571446
EQ-Bench Creative Writing752—

Frequently asked questions

Is GPT-4 better than Qwen3 Max?

Qwen3 Max is the stronger model overall, scoring 43.7 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or Qwen3 Max?

Qwen3 Max is cheaper. It lists at $1.20 per million input tokens and $6 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or Qwen3 Max better for coding?

Qwen3 Max scores higher on coding benchmarks: 43.0 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Qwen3 Max does, with 262K tokens against 8K.

How many benchmarks do GPT-4 and Qwen3 Max share?

25 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Qwen3 Max has 33.

Related comparisons

Go deeper