Noometry

Model comparison

GPT-4 vs Qwen3.7 Plus

Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 29.1 on the Noometry Index.

Last verified . 24 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Qwen3.7 Plus Alibaba (Qwen)

45.3

Rank #72 Confirmed

Summary

  • They share 24 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Qwen3.7 Plus in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.7 Plus leads 50.5 to 10.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for GPT-4 and 93.3% for Qwen3.7 Plus.
  • Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $30 / $60 for GPT-4.
  • Qwen3.7 Plus accepts more context: 1M tokens versus 8K.

Side by side

GPT-4Qwen3.7 Plus
ProviderOpenAIAlibaba (Qwen)
Noometry Index29.145.3
Released2023-03-142026-06-02
WeightsProprietaryProprietary
Context window8K1M
Max output8K131K
Input $ / M tokens$30$0.40
Output $ / M tokens$60$1.60
Results tracked3832

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

Category by category

Coding Qwen3.7 Plus leads

GPT-4: 31.6 (#283), Qwen3.7 Plus: 36.6 (#206)

BenchmarkGPT-4Qwen3.7 Plus
LMArena Coding12541473
FrontierCode—10.2%
SciCode—45.5%
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Qwen3.7 Plus: 21.4 (#138)

BenchmarkGPT-4Qwen3.7 Plus
OSWorld 2.0—2.8%
METR Time Horizons36.1%—

Reasoning Qwen3.7 Plus leads

GPT-4: 17.8 (#289), Qwen3.7 Plus: 39.3 (#59)

BenchmarkGPT-4Qwen3.7 Plus
Chess Puzzles4%24%
LMArena Hard Prompts12411460
Mystery Game Puzzles12%17%
DTBench62.7%84%
LMCA17.1%37.6%
Epoch Capabilities Index125.89147.37
NYT Connections (extended)—74.8%
CritPt—9.1%
BIG-Bench Hard75.1%—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Qwen3.7 Plus leads

GPT-4: 10.8 (#309), Qwen3.7 Plus: 50.5 (#56)

BenchmarkGPT-4Qwen3.7 Plus
OTIS Mock AIME 2024-20251.1%93.3%
LMArena Math12691466
FrontierMath (Tiers 1-3)—34.4%
MATH Level 523%—
GSM8K92%—

Knowledge Qwen3.7 Plus leads

GPT-4: 18.4 (#282), Qwen3.7 Plus: 54.9 (#51)

BenchmarkGPT-4Qwen3.7 Plus
GPQA Diamond35.7%87.9%
LMArena Expert12111467
MMLU86.4%—
TriviaQA84.8%—

Multimodal Not comparable

GPT-4: —, Qwen3.7 Plus: 41.8 (#33)

BenchmarkGPT-4Qwen3.7 Plus
LMArena Vision—1279
LMArena Document—1444

Multilingual Qwen3.7 Plus leads

GPT-4: 40.6 (#215), Qwen3.7 Plus: 54.8 (#38)

BenchmarkGPT-4Qwen3.7 Plus
LMArena Non-English12461445
LMArena Chinese12421510
LMArena French12831473
LMArena German12511471
LMArena Japanese12091413
LMArena Korean11841415
LMArena Russian12511457
LMArena Spanish12611457

Instruction Following Qwen3.7 Plus leads

GPT-4: 65.3 (#222), Qwen3.7 Plus: 75.8 (#52)

BenchmarkGPT-4Qwen3.7 Plus
LMArena Instruction Following12411440

Long Context Qwen3.7 Plus leads

GPT-4: 37.7 (#212), Qwen3.7 Plus: 44.5 (#65)

BenchmarkGPT-4Qwen3.7 Plus
LMArena Longer Query12441455

Writing & Preference Qwen3.7 Plus leads

GPT-4: 34.9 (#268), Qwen3.7 Plus: 64.3 (#56)

BenchmarkGPT-4Qwen3.7 Plus
LMArena Text12631455
LMArena Creative Writing12441439
LMArena Multi-Turn12571460
EQ-Bench Creative Writing752—

Frequently asked questions

Is GPT-4 better than Qwen3.7 Plus?

Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 29.1 on the Noometry Index.

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

Qwen3.7 Plus is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; GPT-4 lists at $30 and $60.

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

Qwen3.7 Plus scores higher on coding benchmarks: 36.6 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

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

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

24 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Qwen3.7 Plus has 32.

Related comparisons

Go deeper