Noometry

Model comparison

GPT-4 vs Qwen Plus

Qwen Plus is the stronger model overall, scoring 37.1 to 29.1 on the Noometry Index.

Last verified . 18 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Qwen Plus Alibaba (Qwen)

37.1

Rank #210 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Qwen Plus in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Qwen Plus leads 52.2 to 34.9.
  • The biggest single-benchmark swing is MATH Level 5: 23% for GPT-4 and 65.3% for Qwen Plus.
  • Qwen Plus is cheaper at $0.40 / $1.20 per million input/output tokens, against $30 / $60 for GPT-4.
  • Qwen Plus accepts more context: 1M tokens versus 8K.

Side by side

GPT-4Qwen Plus
ProviderOpenAIAlibaba (Qwen)
Noometry Index29.137.1
Released2023-03-142024-01-25
WeightsProprietaryProprietary
Context window8K1M
Max output8K33K
Input $ / M tokens$30$0.40
Output $ / M tokens$60$1.20
Results tracked3820

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

Category by category

Coding Qwen Plus leads

GPT-4: 31.6 (#283), Qwen Plus: 38.9 (#167)

BenchmarkGPT-4Qwen Plus
LMArena Coding12541328
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Qwen Plus: —

BenchmarkGPT-4Qwen Plus
METR Time Horizons36.1%—

Reasoning Qwen Plus leads

GPT-4: 17.8 (#289), Qwen Plus: 28.4 (#107)

BenchmarkGPT-4Qwen Plus
LMArena Hard Prompts12411317
DTBench62.7%81.1%
LMCA17.1%24%
Kagi LLM Benchmark—63.3%
Chess Puzzles4%—
Mystery Game Puzzles12%—
BIG-Bench Hard75.1%—
Epoch Capabilities Index125.89—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Qwen Plus leads

GPT-4: 10.8 (#309), Qwen Plus: 23.3 (#271)

BenchmarkGPT-4Qwen Plus
OTIS Mock AIME 2024-20251.1%17.8%
LMArena Math12691326
MATH Level 523%65.3%
FrontierMath (Feb 2025 set)—1.7%
GSM8K92%—

Knowledge Qwen Plus leads

GPT-4: 18.4 (#282), Qwen Plus: 27.4 (#251)

BenchmarkGPT-4Qwen Plus
GPQA Diamond35.7%48.1%
LMArena Expert12111328
MMLU86.4%—
TriviaQA84.8%—

Multilingual Qwen Plus leads

GPT-4: 40.6 (#215), Qwen Plus: 45.1 (#175)

BenchmarkGPT-4Qwen Plus
LMArena Non-English12461310
LMArena Chinese12421347
LMArena Japanese12091251
LMArena Russian12511323
LMArena French1283—
LMArena German1251—
LMArena Korean1184—
LMArena Spanish1261—

Instruction Following Qwen Plus leads

GPT-4: 65.3 (#222), Qwen Plus: 68.8 (#181)

BenchmarkGPT-4Qwen Plus
LMArena Instruction Following12411303

Long Context Qwen Plus leads

GPT-4: 37.7 (#212), Qwen Plus: 40.3 (#158)

BenchmarkGPT-4Qwen Plus
LMArena Longer Query12441324

Writing & Preference Qwen Plus leads

GPT-4: 34.9 (#268), Qwen Plus: 52.2 (#176)

BenchmarkGPT-4Qwen Plus
LMArena Text12631326
LMArena Creative Writing12441293
LMArena Multi-Turn12571336
EQ-Bench Creative Writing752—

Frequently asked questions

Is GPT-4 better than Qwen Plus?

Qwen Plus is the stronger model overall, scoring 37.1 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or Qwen Plus?

Qwen Plus is cheaper. It lists at $0.40 per million input tokens and $1.20 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or Qwen Plus better for coding?

Qwen Plus scores higher on coding benchmarks: 38.9 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Qwen Plus does, with 1M tokens against 8K.

How many benchmarks do GPT-4 and Qwen Plus share?

18 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Qwen Plus has 20.

Related comparisons

Go deeper