Noometry

Model comparison

Qwen1.5 4b Chat vs Qwen2.5 72B Instruct

Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 28.8 on the Noometry Index.

Last verified . 13 shared benchmarks.

Qwen1.5 4b Chat Alibaba (Qwen)

28.8

Rank #322 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.9

Rank #267 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Qwen1.5 4b Chat scores higher in 1 category and Qwen2.5 72B Instruct in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Qwen2.5 72B Instruct leads 46.7 to 23.8.

Side by side

Qwen1.5 4b ChatQwen2.5 72B Instruct
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index28.831.9
Released—2024-09
WeightsOpenOpen
Context window—131K
Max output—8K
Input $ / M tokens—$1.40
Output $ / M tokens—$5.60
Results tracked1343

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

Category by category

Coding Qwen2.5 72B Instruct leads

Qwen1.5 4b Chat: 29.1 (#308), Qwen2.5 72B Instruct: 33.2 (#260)

BenchmarkQwen1.5 4b ChatQwen2.5 72B Instruct
LMArena Coding9991292
WeirdML—16%
BigCodeBench Instruct—45.8%
BigCodeBench Complete—55.9%

Agentic & Tool Use Not comparable

Qwen1.5 4b Chat: —, Qwen2.5 72B Instruct: 22.1 (#133)

BenchmarkQwen1.5 4b ChatQwen2.5 72B Instruct
TheAgentCompany—5.7%
BALROG—16.2%
METR Time Horizons—35.8%

Reasoning Qwen2.5 72B Instruct leads

Qwen1.5 4b Chat: 18.5 (#279), Qwen2.5 72B Instruct: 22.3 (#199)

BenchmarkQwen1.5 4b ChatQwen2.5 72B Instruct
LMArena Hard Prompts9761271
DTBench—62.9%
LMCA—13.4%
BIG-Bench Hard—79.8%
Epoch Capabilities Index—129
ForecastBench—57.5
HellaSwag—84.8%
PIQA—82.6%
WinoGrande—82.3%

Math Qwen1.5 4b Chat leads

Qwen1.5 4b Chat: 30.4 (#234), Qwen2.5 72B Instruct: 19.3 (#287)

BenchmarkQwen1.5 4b ChatQwen2.5 72B Instruct
LMArena Math10261283
OTIS Mock AIME 2024-2025—8.1%
Omni-MATH—33%
MATH Level 5—63.2%

Knowledge Too close to call

Qwen1.5 4b Chat: 26.7 (#255), Qwen2.5 72B Instruct: 27.0 (#253)

BenchmarkQwen1.5 4b ChatQwen2.5 72B Instruct
LMArena Expert9801245
GPQA Diamond—49.1%
MMLU-Pro—63.1%
Confabulations—19.1%
GPQA (HELM)—42.6%
ARC (AI2) Challenge—94.5%
MMLU—85.3%
TriviaQA—71.9%

Multilingual Qwen2.5 72B Instruct leads

Qwen1.5 4b Chat: 24.1 (#290), Qwen2.5 72B Instruct: 41.0 (#213)

BenchmarkQwen1.5 4b ChatQwen2.5 72B Instruct
LMArena Non-English9791252
LMArena Chinese10241272
LMArena German9021234
LMArena Russian9521264
LMArena French—1280
LMArena Japanese—1180
LMArena Korean—1188
LMArena Spanish—1256

Instruction Following Qwen2.5 72B Instruct leads

Qwen1.5 4b Chat: 49.0 (#300), Qwen2.5 72B Instruct: 65.5 (#221)

BenchmarkQwen1.5 4b ChatQwen2.5 72B Instruct
LMArena Instruction Following9781254
IFEval—80.6%

Long Context Qwen2.5 72B Instruct leads

Qwen1.5 4b Chat: 30.1 (#290), Qwen2.5 72B Instruct: 38.9 (#188)

BenchmarkQwen1.5 4b ChatQwen2.5 72B Instruct
LMArena Longer Query9881282

Writing & Preference Qwen2.5 72B Instruct leads

Qwen1.5 4b Chat: 23.8 (#309), Qwen2.5 72B Instruct: 46.7 (#215)

BenchmarkQwen1.5 4b ChatQwen2.5 72B Instruct
LMArena Text9971269
LMArena Creative Writing9691221
LMArena Multi-Turn9771272
WildBench—80.2%

Frequently asked questions

Is Qwen1.5 4b Chat better than Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 28.8 on the Noometry Index.

Is Qwen1.5 4b Chat or Qwen2.5 72B Instruct better for coding?

Qwen2.5 72B Instruct scores higher on coding benchmarks: 33.2 versus 29.1 in the Noometry coding category.

How many benchmarks do Qwen1.5 4b Chat and Qwen2.5 72B Instruct share?

13 benchmarks have published results for both models. Qwen1.5 4b Chat has 13 scored results on Noometry and Qwen2.5 72B Instruct has 43.

Related comparisons

Go deeper