Noometry

Model comparison

GPT-4 Turbo vs Qwen Max

Qwen Max is the stronger model overall, scoring 34.4 to 30.3 on the Noometry Index.

Last verified . 20 shared benchmarks.

GPT-4 Turbo OpenAI

30.3

Rank #281 Confirmed

Qwen Max Alibaba (Qwen)

34.4

Rank #226 Confirmed

Summary

  • They share 20 benchmarks with published results for both. GPT-4 Turbo scores higher in 1 category and Qwen Max in 7 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen Max leads 21.0 to 8.6.
  • The biggest single-benchmark swing is MATH Level 5: 46.7% for GPT-4 Turbo and 67.2% for Qwen Max.
  • Qwen Max is cheaper at $1.60 / $6.40 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • GPT-4 Turbo accepts more context: 128K tokens versus 33K.

Side by side

GPT-4 TurboQwen Max
ProviderOpenAIAlibaba (Qwen)
Noometry Index30.334.4
Released2023-11-062024-04-03
WeightsProprietaryProprietary
Context window128K33K
Max output4K8K
Input $ / M tokens$10$1.60
Output $ / M tokens$30$6.40
Results tracked3623

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

Category by category

Coding GPT-4 Turbo leads

GPT-4 Turbo: 33.4 (#247), Qwen Max: 30.3 (#288)

BenchmarkGPT-4 TurboQwen Max
LMArena Coding12681288
Aider Polyglot—21.8%
WeirdML18%—
BigCodeBench Instruct48.2%—
BigCodeBench Complete58.2%—
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, Qwen Max: —

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

Reasoning Qwen Max leads

GPT-4 Turbo: 14.9 (#311), Qwen Max: 24.1 (#154)

BenchmarkGPT-4 TurboQwen Max
LMArena Hard Prompts12511270
SimpleBench25.1%—
Chess Puzzles6%—
DTBench61.6%—
LMCA9.8%—
Epoch Capabilities Index127.25—
ForecastBench59.4—

Math Qwen Max leads

GPT-4 Turbo: 8.6 (#316), Qwen Max: 21.0 (#272)

BenchmarkGPT-4 TurboQwen Max
OTIS Mock AIME 2024-20256.7%16.1%
LMArena Math12721275
MATH Level 546.7%67.2%
FrontierMath (Tiers 1-3)0.7%—
FrontierMath (Feb 2025 set)—1%

Knowledge Qwen Max leads

GPT-4 Turbo: 24.3 (#263), Qwen Max: 30.3 (#222)

BenchmarkGPT-4 TurboQwen Max
GPQA Diamond46.6%56.1%
LMArena Expert12231248
Confabulations28.4%—
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.0 (#104), Qwen Max: —

BenchmarkGPT-4 TurboQwen Max
LMArena Vision1090—

Multilingual Qwen Max leads

GPT-4 Turbo: 40.7 (#211), Qwen Max: 42.0 (#197)

BenchmarkGPT-4 TurboQwen Max
LMArena Non-English12451263
LMArena Chinese12421254
LMArena French12751329
LMArena German12591254
LMArena Japanese11941205
LMArena Korean11871141
LMArena Russian12591274
LMArena Spanish12601290

Instruction Following Too close to call

GPT-4 Turbo: 66.0 (#211), Qwen Max: 66.7 (#203)

BenchmarkGPT-4 TurboQwen Max
LMArena Instruction Following12501262

Long Context Qwen Max leads

GPT-4 Turbo: 38.0 (#200), Qwen Max: 39.4 (#175)

BenchmarkGPT-4 TurboQwen Max
LMArena Longer Query12541289
Fiction.LiveBench—66.7%

Writing & Preference Too close to call

GPT-4 Turbo: 47.9 (#201), Qwen Max: 48.0 (#200)

BenchmarkGPT-4 TurboQwen Max
LMArena Text12721282
LMArena Creative Writing12691248
LMArena Multi-Turn12671277

Frequently asked questions

Is GPT-4 Turbo better than Qwen Max?

Qwen Max is the stronger model overall, scoring 34.4 to 30.3 on the Noometry Index.

Which is cheaper, GPT-4 Turbo or Qwen Max?

Qwen Max is cheaper. It lists at $1.60 per million input tokens and $6.40 per million output tokens; GPT-4 Turbo lists at $10 and $30.

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

GPT-4 Turbo scores higher on coding benchmarks: 33.4 versus 30.3 in the Noometry coding category.

Which has the bigger context window?

GPT-4 Turbo does, with 128K tokens against 33K.

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

20 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Qwen Max has 23.

Related comparisons

Go deeper