Noometry

Model comparison

GPT-4 vs Qwen3.6 Plus

Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 29.1 on the Noometry Index.

Last verified . 24 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Qwen3.6 Plus Alibaba (Qwen)

47.5

Rank #62 Confirmed

Summary

  • They share 24 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Qwen3.6 Plus in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.6 Plus leads 51.8 to 10.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for GPT-4 and 93.3% for Qwen3.6 Plus.
  • Qwen3.6 Plus is cheaper at $0.50 / $3 per million input/output tokens, against $30 / $60 for GPT-4.
  • Qwen3.6 Plus accepts more context: 1M tokens versus 8K.

Side by side

GPT-4Qwen3.6 Plus
ProviderOpenAIAlibaba (Qwen)
Noometry Index29.147.5
Released2023-03-142026-03-31
WeightsProprietaryProprietary
Context window8K1M
Max output8K66K
Input $ / M tokens$30$0.50
Output $ / M tokens$60$3
Results tracked3837

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

Category by category

Coding Qwen3.6 Plus leads

GPT-4: 31.6 (#283), Qwen3.6 Plus: 40.8 (#130)

BenchmarkGPT-4Qwen3.6 Plus
LMArena Coding12541467
SWE-bench Verified—57.9%
LMArena WebDev—1461
SciCode—40.7%
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
ALE-Bench—670.15
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Qwen3.6 Plus: —

BenchmarkGPT-4Qwen3.6 Plus
METR Time Horizons36.1%—
Vending-Bench 2—5,115

Reasoning Qwen3.6 Plus leads

GPT-4: 17.8 (#289), Qwen3.6 Plus: 29.3 (#93)

BenchmarkGPT-4Qwen3.6 Plus
Chess Puzzles4%17%
LMArena Hard Prompts12411449
Mystery Game Puzzles12%12%
DTBench62.7%81.9%
LMCA17.1%33.1%
Epoch Capabilities Index125.89147.65
NYT Connections (extended)—60.3%
CritPt—2.9%
Thematic Generalization—59.5%
BIG-Bench Hard75.1%—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Qwen3.6 Plus leads

GPT-4: 10.8 (#309), Qwen3.6 Plus: 51.8 (#54)

BenchmarkGPT-4Qwen3.6 Plus
OTIS Mock AIME 2024-20251.1%93.3%
LMArena Math12691450
FrontierMath (Tiers 1-3)—38.2%
MATH Level 523%—
FrontierMath (Feb 2025 set)—26.2%
FrontierMath Tier 4 (v1)—8.3%
GSM8K92%—

Knowledge Qwen3.6 Plus leads

GPT-4: 18.4 (#282), Qwen3.6 Plus: 56.1 (#45)

BenchmarkGPT-4Qwen3.6 Plus
GPQA Diamond35.7%88.4%
LMArena Expert12111454
SimpleQA Verified—44.1%
MMLU86.4%—
TriviaQA84.8%—

Multilingual Qwen3.6 Plus leads

GPT-4: 40.6 (#215), Qwen3.6 Plus: 53.3 (#70)

BenchmarkGPT-4Qwen3.6 Plus
LMArena Non-English12461424
LMArena Chinese12421477
LMArena French12831455
LMArena German12511452
LMArena Japanese12091389
LMArena Korean11841379
LMArena Russian12511434
LMArena Spanish12611432

Instruction Following Qwen3.6 Plus leads

GPT-4: 65.3 (#222), Qwen3.6 Plus: 75.0 (#74)

BenchmarkGPT-4Qwen3.6 Plus
LMArena Instruction Following12411425

Long Context Qwen3.6 Plus leads

GPT-4: 37.7 (#212), Qwen3.6 Plus: 45.2 (#49)

BenchmarkGPT-4Qwen3.6 Plus
LMArena Longer Query12441439
CL-bench—20.3%

Writing & Preference Qwen3.6 Plus leads

GPT-4: 34.9 (#268), Qwen3.6 Plus: 62.2 (#82)

BenchmarkGPT-4Qwen3.6 Plus
LMArena Text12631437
LMArena Creative Writing12441404
LMArena Multi-Turn12571438
EQ-Bench Creative Writing752—

Frequently asked questions

Is GPT-4 better than Qwen3.6 Plus?

Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or Qwen3.6 Plus?

Qwen3.6 Plus is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or Qwen3.6 Plus better for coding?

Qwen3.6 Plus scores higher on coding benchmarks: 40.8 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Qwen3.6 Plus does, with 1M tokens against 8K.

How many benchmarks do GPT-4 and Qwen3.6 Plus share?

24 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Qwen3.6 Plus has 37.

Related comparisons

Go deeper