Noometry

Model comparison

GPT-4 Turbo vs Qwen Plus

Qwen Plus is the stronger model overall, scoring 36.7 to 30.3 on the Noometry Index.

Last verified . 18 shared benchmarks.

GPT-4 Turbo OpenAI

30.3

Rank #281 Confirmed

Qwen Plus Alibaba (Qwen)

36.7

Rank #204 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and Qwen Plus in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen Plus leads 22.0 to 8.6.
  • The biggest single-benchmark swing is DTBench: 61.6% for GPT-4 Turbo and 81.1% for Qwen Plus.
  • Qwen Plus is cheaper at $0.40 / $1.20 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • Qwen Plus accepts more context: 1M tokens versus 128K.

Side by side

GPT-4 TurboQwen Plus
ProviderOpenAIAlibaba (Qwen)
Noometry Index30.336.7
Released2023-11-062024-01-25
WeightsProprietaryProprietary
Context window128K1M
Max output4K33K
Input $ / M tokens$10$0.40
Output $ / M tokens$30$1.20
Results tracked3620

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

Category by category

Coding Qwen Plus leads

GPT-4 Turbo: 33.4 (#247), Qwen Plus: 38.3 (#163)

BenchmarkGPT-4 TurboQwen Plus
LMArena Coding12681328
WeirdML18%—
BigCodeBench Instruct48.2%—
BigCodeBench Complete58.2%—
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, Qwen Plus: —

BenchmarkGPT-4 TurboQwen Plus
METR Time Horizons36.7%—

Reasoning Qwen Plus leads

GPT-4 Turbo: 14.9 (#311), Qwen Plus: 27.6 (#101)

BenchmarkGPT-4 TurboQwen Plus
LMArena Hard Prompts12511317
DTBench61.6%81.1%
LMCA9.8%24%
SimpleBench25.1%—
Kagi LLM Benchmark—63.3%
Chess Puzzles6%—
Epoch Capabilities Index127.25—
ForecastBench59.4—

Math Qwen Plus leads

GPT-4 Turbo: 8.6 (#316), Qwen Plus: 22.0 (#266)

BenchmarkGPT-4 TurboQwen Plus
OTIS Mock AIME 2024-20256.7%17.8%
LMArena Math12721326
MATH Level 546.7%65.3%
FrontierMath (Tiers 1-3)0.7%—
FrontierMath (Feb 2025 set)—1.7%

Knowledge Qwen Plus leads

GPT-4 Turbo: 24.3 (#263), Qwen Plus: 27.4 (#245)

BenchmarkGPT-4 TurboQwen Plus
GPQA Diamond46.6%48.1%
LMArena Expert12231328
Confabulations28.4%—
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.0 (#104), Qwen Plus: —

BenchmarkGPT-4 TurboQwen Plus
LMArena Vision1090—

Multilingual Qwen Plus leads

GPT-4 Turbo: 40.7 (#211), Qwen Plus: 45.3 (#170)

BenchmarkGPT-4 TurboQwen Plus
LMArena Non-English12451310
LMArena Chinese12421347
LMArena Japanese11941251
LMArena Russian12591323
LMArena French1275—
LMArena German1259—
LMArena Korean1187—
LMArena Spanish1260—

Instruction Following Qwen Plus leads

GPT-4 Turbo: 66.0 (#211), Qwen Plus: 69.0 (#176)

BenchmarkGPT-4 TurboQwen Plus
LMArena Instruction Following12501303

Long Context Qwen Plus leads

GPT-4 Turbo: 38.0 (#200), Qwen Plus: 40.3 (#153)

BenchmarkGPT-4 TurboQwen Plus
LMArena Longer Query12541325

Writing & Preference Qwen Plus leads

GPT-4 Turbo: 47.9 (#201), Qwen Plus: 52.4 (#171)

BenchmarkGPT-4 TurboQwen Plus
LMArena Text12721326
LMArena Creative Writing12691293
LMArena Multi-Turn12671336

Frequently asked questions

Is GPT-4 Turbo better than Qwen Plus?

Qwen Plus is the stronger model overall, scoring 36.7 to 30.3 on the Noometry Index.

Which is cheaper, GPT-4 Turbo 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 Turbo lists at $10 and $30.

Is GPT-4 Turbo or Qwen Plus better for coding?

Qwen Plus scores higher on coding benchmarks: 38.3 versus 33.4 in the Noometry coding category.

Which has the bigger context window?

Qwen Plus does, with 1M tokens against 128K.

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

18 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Qwen Plus has 20.

Related comparisons

Go deeper