Noometry

Model comparison

Qwen2.5 72B Instruct vs Qwen2.5-Max

Qwen2.5-Max is the stronger model overall, scoring 40.7 to 31.9 on the Noometry Index.

Last verified . 19 shared benchmarks.

Qwen2.5 72B Instruct Alibaba (Qwen)

31.9

Rank #267 Confirmed

Qwen2.5-Max Alibaba (Qwen)

40.7

Rank #146 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Qwen2.5 72B Instruct 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 36.9 to 19.3.
  • Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.

Side by side

Qwen2.5 72B InstructQwen2.5-Max
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index31.940.7
Released2024-092025-01-25
WeightsOpenProprietary
Context window131K—
Max output8K—
Input $ / M tokens$1.40—
Output $ / M tokens$5.60—
Results tracked4327

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

Category by category

Coding Qwen2.5-Max leads

Qwen2.5 72B Instruct: 33.2 (#260), Qwen2.5-Max: 41.8 (#117)

BenchmarkQwen2.5 72B InstructQwen2.5-Max
LMArena Coding12921359
WeirdML16%—
BigCodeBench Instruct45.8%—
LiveBench Coding—64.4%
BigCodeBench Complete55.9%—

Agentic & Tool Use Not comparable

Qwen2.5 72B Instruct: 22.1 (#133), Qwen2.5-Max: —

BenchmarkQwen2.5 72B InstructQwen2.5-Max
TheAgentCompany5.7%—
BALROG16.2%—
METR Time Horizons35.8%—

Reasoning Qwen2.5-Max leads

Qwen2.5 72B Instruct: 22.3 (#199), Qwen2.5-Max: 25.6 (#147)

BenchmarkQwen2.5 72B InstructQwen2.5-Max
LMArena Hard Prompts12711360
Epoch Capabilities Index129132.53
LiveBench Reasoning—51.4%
DTBench62.9%—
LiveBench Data Analysis—67.9%
LMCA13.4%—
BIG-Bench Hard79.8%—
ForecastBench57.5—
HellaSwag84.8%—
LiveBench—62.3%
PIQA82.6%—
WinoGrande82.3%—

Math Qwen2.5-Max leads

Qwen2.5 72B Instruct: 19.3 (#287), Qwen2.5-Max: 36.9 (#162)

BenchmarkQwen2.5 72B InstructQwen2.5-Max
LMArena Math12831369
OTIS Mock AIME 2024-20258.1%—
Omni-MATH33%—
LiveBench Math—58.4%
MATH Level 563.2%—

Knowledge Qwen2.5-Max leads

Qwen2.5 72B Instruct: 27.0 (#253), Qwen2.5-Max: 35.3 (#186)

BenchmarkQwen2.5 72B InstructQwen2.5-Max
Confabulations19.1%21.8%
LMArena Expert12451337
GPQA Diamond49.1%—
MMLU-Pro63.1%—
GPQA (HELM)42.6%—
ARC (AI2) Challenge94.5%—
MMLU85.3%—
TriviaQA71.9%—

Multilingual Qwen2.5-Max leads

Qwen2.5 72B Instruct: 41.0 (#213), Qwen2.5-Max: 48.1 (#146)

BenchmarkQwen2.5 72B InstructQwen2.5-Max
LMArena Non-English12521352
LMArena Chinese12721382
LMArena French12801396
LMArena German12341350
LMArena Japanese11801300
LMArena Korean11881304
LMArena Russian12641353
LMArena Spanish12561377

Instruction Following Qwen2.5-Max leads

Qwen2.5 72B Instruct: 65.5 (#221), Qwen2.5-Max: 71.3 (#152)

BenchmarkQwen2.5 72B InstructQwen2.5-Max
LMArena Instruction Following12541335
LiveBench Instruction Following—75.3%
IFEval80.6%—

Long Context Qwen2.5-Max leads

Qwen2.5 72B Instruct: 38.9 (#188), Qwen2.5-Max: 41.4 (#142)

BenchmarkQwen2.5 72B InstructQwen2.5-Max
LMArena Longer Query12821358

Writing & Preference Qwen2.5-Max leads

Qwen2.5 72B Instruct: 46.7 (#215), Qwen2.5-Max: 55.4 (#146)

BenchmarkQwen2.5 72B InstructQwen2.5-Max
LMArena Text12691367
LMArena Creative Writing12211339
LMArena Multi-Turn12721364
Short-Story Creative Writing—72.9%
WildBench80.2%—
LiveBench Language—56.3%

Frequently asked questions

Is Qwen2.5 72B Instruct better than Qwen2.5-Max?

Qwen2.5-Max is the stronger model overall, scoring 40.7 to 31.9 on the Noometry Index.

Is Qwen2.5 72B Instruct or Qwen2.5-Max better for coding?

Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 33.2 in the Noometry coding category.

How many benchmarks do Qwen2.5 72B Instruct and Qwen2.5-Max share?

19 benchmarks have published results for both models. Qwen2.5 72B Instruct has 43 scored results on Noometry and Qwen2.5-Max has 27.

Related comparisons

Go deeper