Noometry

Model comparison

GPT-4 vs Qwen3.7 Max

Qwen3.7 Max is the stronger model overall, scoring 51.5 to 29.1 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Qwen3.7 Max Alibaba (Qwen)

51.5

Rank #42 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Qwen3.7 Max in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.7 Max leads 62.4 to 10.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for GPT-4 and 95.6% for Qwen3.7 Max.
  • Qwen3.7 Max is cheaper at $2.50 / $7.50 per million input/output tokens, against $30 / $60 for GPT-4.
  • Qwen3.7 Max accepts more context: 1M tokens versus 8K.

Side by side

GPT-4Qwen3.7 Max
ProviderOpenAIAlibaba (Qwen)
Noometry Index29.151.5
Released2023-03-142026-05-19
WeightsProprietaryProprietary
Context window8K1M
Max output8K131K
Input $ / M tokens$30$2.50
Output $ / M tokens$60$7.50
Results tracked3833

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

Category by category

Coding Qwen3.7 Max leads

GPT-4: 31.6 (#283), Qwen3.7 Max: 50.4 (#45)

BenchmarkGPT-4Qwen3.7 Max
LMArena Coding12541498
SWE-bench Verified—77.3%
LMArena WebDev—1515
SciCode—48.8%
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
ALE-Bench—1,189
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Qwen3.7 Max: 22.1 (#135)

BenchmarkGPT-4Qwen3.7 Max
GBAEval—0.4%
METR Time Horizons36.1%—

Reasoning Qwen3.7 Max leads

GPT-4: 17.8 (#289), Qwen3.7 Max: 49.2 (#38)

BenchmarkGPT-4Qwen3.7 Max
Chess Puzzles4%19%
LMArena Hard Prompts12411483
Mystery Game Puzzles12%32%
DTBench62.7%92.3%
LMCA17.1%44%
Epoch Capabilities Index125.89153.68
SimpleBench—70.4%
NYT Connections (extended)—85.1%
CritPt—13.4%
EBR-Bench—9.5%
BIG-Bench Hard75.1%—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Qwen3.7 Max leads

GPT-4: 10.8 (#309), Qwen3.7 Max: 62.4 (#32)

BenchmarkGPT-4Qwen3.7 Max
OTIS Mock AIME 2024-20251.1%95.6%
LMArena Math12691490
FrontierMath (Tiers 1-3)—64.6%
FrontierMath Tier 4—34.1%
ProofBench—26%
MATH Level 523%—
GSM8K92%—

Knowledge Qwen3.7 Max leads

GPT-4: 18.4 (#282), Qwen3.7 Max: 61.6 (#28)

BenchmarkGPT-4Qwen3.7 Max
GPQA Diamond35.7%90.9%
LMArena Expert12111488
SimpleQA Verified—55.8%
MMLU86.4%—
TriviaQA84.8%—

Multilingual Qwen3.7 Max leads

GPT-4: 40.6 (#215), Qwen3.7 Max: 56.9 (#15)

BenchmarkGPT-4Qwen3.7 Max
LMArena Non-English12461474
LMArena Chinese12421530
LMArena Russian12511484
LMArena French1283—
LMArena German1251—
LMArena Japanese1209—
LMArena Korean1184—
LMArena Spanish1261—

Instruction Following Qwen3.7 Max leads

GPT-4: 65.3 (#222), Qwen3.7 Max: 76.7 (#38)

BenchmarkGPT-4Qwen3.7 Max
LMArena Instruction Following12411460

Long Context Qwen3.7 Max leads

GPT-4: 37.7 (#212), Qwen3.7 Max: 45.4 (#40)

BenchmarkGPT-4Qwen3.7 Max
LMArena Longer Query12441482

Writing & Preference Qwen3.7 Max leads

GPT-4: 34.9 (#268), Qwen3.7 Max: 65.0 (#54)

BenchmarkGPT-4Qwen3.7 Max
LMArena Text12631476
LMArena Creative Writing12441449
LMArena Multi-Turn12571481
EQ-Bench Creative Writing752—
EQ-Bench 4—1110

Frequently asked questions

Is GPT-4 better than Qwen3.7 Max?

Qwen3.7 Max is the stronger model overall, scoring 51.5 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or Qwen3.7 Max?

Qwen3.7 Max is cheaper. It lists at $2.50 per million input tokens and $7.50 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or Qwen3.7 Max better for coding?

Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Qwen3.7 Max does, with 1M tokens against 8K.

How many benchmarks do GPT-4 and Qwen3.7 Max share?

19 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Qwen3.7 Max has 33.

Related comparisons

Go deeper