Noometry

Model comparison

GPT-4 Turbo vs Qwen2.5-Max

Qwen2.5-Max is the stronger model overall, scoring 40.1 to 30.3 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-4 Turbo OpenAI

30.3

Rank #281 Confirmed

Qwen2.5-Max Alibaba (Qwen)

40.1

Rank #142 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen2.5-Max leads 34.3 to 8.6.
  • The biggest single-benchmark swing is Confabulations: 28.4% for GPT-4 Turbo and 21.8% for Qwen2.5-Max.

Side by side

GPT-4 TurboQwen2.5-Max
ProviderOpenAIAlibaba (Qwen)
Noometry Index30.340.1
Released2023-11-062025-01-25
WeightsProprietaryProprietary
Context window128K—
Max output4K—
Input $ / M tokens$10—
Output $ / M tokens$30—
Results tracked3627

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

Category by category

Coding Qwen2.5-Max leads

GPT-4 Turbo: 33.4 (#247), Qwen2.5-Max: 41.2 (#118)

BenchmarkGPT-4 TurboQwen2.5-Max
LMArena Coding12681359
WeirdML18%—
BigCodeBench Instruct48.2%—
LiveBench Coding—64.4%
BigCodeBench Complete58.2%—
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, Qwen2.5-Max: —

BenchmarkGPT-4 TurboQwen2.5-Max
METR Time Horizons36.7%—

Reasoning Qwen2.5-Max leads

GPT-4 Turbo: 14.9 (#311), Qwen2.5-Max: 24.6 (#144)

BenchmarkGPT-4 TurboQwen2.5-Max
LMArena Hard Prompts12511360
Epoch Capabilities Index127.25132.54
SimpleBench25.1%—
Chess Puzzles6%—
LiveBench Reasoning—51.4%
DTBench61.6%—
LiveBench Data Analysis—67.9%
LMCA9.8%—
ForecastBench59.4—
LiveBench—62.3%

Math Qwen2.5-Max leads

GPT-4 Turbo: 8.6 (#316), Qwen2.5-Max: 34.3 (#162)

BenchmarkGPT-4 TurboQwen2.5-Max
LMArena Math12721369
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.7%—
LiveBench Math—58.4%
MATH Level 546.7%—

Knowledge Qwen2.5-Max leads

GPT-4 Turbo: 24.3 (#263), Qwen2.5-Max: 34.8 (#181)

BenchmarkGPT-4 TurboQwen2.5-Max
Confabulations28.4%21.8%
LMArena Expert12231337
GPQA Diamond46.6%—
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.0 (#104), Qwen2.5-Max: —

BenchmarkGPT-4 TurboQwen2.5-Max
LMArena Vision1090—

Multilingual Qwen2.5-Max leads

GPT-4 Turbo: 40.7 (#211), Qwen2.5-Max: 48.3 (#140)

BenchmarkGPT-4 TurboQwen2.5-Max
LMArena Non-English12451352
LMArena Chinese12421382
LMArena French12751396
LMArena German12591350
LMArena Japanese11941299
LMArena Korean11871304
LMArena Russian12591353
LMArena Spanish12601377

Instruction Following Qwen2.5-Max leads

GPT-4 Turbo: 66.0 (#211), Qwen2.5-Max: 71.5 (#147)

BenchmarkGPT-4 TurboQwen2.5-Max
LMArena Instruction Following12501335
LiveBench Instruction Following—75.3%

Long Context Qwen2.5-Max leads

GPT-4 Turbo: 38.0 (#200), Qwen2.5-Max: 41.3 (#137)

BenchmarkGPT-4 TurboQwen2.5-Max
LMArena Longer Query12541358

Writing & Preference Qwen2.5-Max leads

GPT-4 Turbo: 47.9 (#201), Qwen2.5-Max: 55.6 (#141)

BenchmarkGPT-4 TurboQwen2.5-Max
LMArena Text12721367
LMArena Creative Writing12691339
LMArena Multi-Turn12671364
Short-Story Creative Writing—72.9%
LiveBench Language—56.3%

Frequently asked questions

Is GPT-4 Turbo better than Qwen2.5-Max?

Qwen2.5-Max is the stronger model overall, scoring 40.1 to 30.3 on the Noometry Index.

Is GPT-4 Turbo or Qwen2.5-Max better for coding?

Qwen2.5-Max scores higher on coding benchmarks: 41.2 versus 33.4 in the Noometry coding category.

How many benchmarks do GPT-4 Turbo and Qwen2.5-Max share?

19 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Qwen2.5-Max has 27.

Related comparisons

Go deeper