Noometry

Model comparison

Qwen1.5-72B vs Qwen2.5 72B Instruct

Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 30.8 on the Noometry Index.

Last verified . 20 shared benchmarks.

Qwen1.5-72B Alibaba (Qwen)

30.8

Rank #285 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.9

Rank #267 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Qwen1.5-72B 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 knowledge, where Qwen2.5 72B Instruct leads 27.0 to 11.5.
  • The biggest single-benchmark swing is GPQA Diamond: 28.8% for Qwen1.5-72B and 49.1% for Qwen2.5 72B Instruct.

Side by side

Qwen1.5-72BQwen2.5 72B Instruct
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index30.831.9
Released2024-02-042024-09
WeightsOpenOpen
Context window—131K
Max output—8K
Input $ / M tokens—$1.40
Output $ / M tokens—$5.60
Results tracked2243

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

Category by category

Coding Qwen2.5 72B Instruct leads

Qwen1.5-72B: 31.9 (#277), Qwen2.5 72B Instruct: 33.2 (#260)

BenchmarkQwen1.5-72BQwen2.5 72B Instruct
BigCodeBench Instruct33.2%45.8%
LMArena Coding11651292
BigCodeBench Complete40.3%55.9%
WeirdML—16%
HumanEval+59.1%—
MBPP+61.6%—

Agentic & Tool Use Not comparable

Qwen1.5-72B: —, Qwen2.5 72B Instruct: 22.1 (#133)

BenchmarkQwen1.5-72BQwen2.5 72B Instruct
TheAgentCompany—5.7%
BALROG—16.2%
METR Time Horizons—35.8%

Reasoning Too close to call

Qwen1.5-72B: 22.2 (#203), Qwen2.5 72B Instruct: 22.3 (#199)

BenchmarkQwen1.5-72BQwen2.5 72B Instruct
LMArena Hard Prompts11481271
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 Qwen1.5-72B leads

Qwen1.5-72B: 33.2 (#205), Qwen2.5 72B Instruct: 19.3 (#287)

BenchmarkQwen1.5-72BQwen2.5 72B Instruct
LMArena Math11641283
OTIS Mock AIME 2024-2025—8.1%
Omni-MATH—33%
MATH Level 5—63.2%

Knowledge Qwen2.5 72B Instruct leads

Qwen1.5-72B: 11.5 (#300), Qwen2.5 72B Instruct: 27.0 (#253)

BenchmarkQwen1.5-72BQwen2.5 72B Instruct
GPQA Diamond28.8%49.1%
LMArena Expert11361245
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

Qwen1.5-72B: 33.2 (#253), Qwen2.5 72B Instruct: 41.0 (#213)

BenchmarkQwen1.5-72BQwen2.5 72B Instruct
LMArena Non-English11351252
LMArena Chinese11861272
LMArena French11591280
LMArena German10841234
LMArena Japanese10611180
LMArena Korean10501188
LMArena Russian11041264
LMArena Spanish11101256

Instruction Following Qwen2.5 72B Instruct leads

Qwen1.5-72B: 59.3 (#256), Qwen2.5 72B Instruct: 65.5 (#221)

BenchmarkQwen1.5-72BQwen2.5 72B Instruct
LMArena Instruction Following11411254
IFEval—80.6%

Long Context Qwen2.5 72B Instruct leads

Qwen1.5-72B: 35.1 (#243), Qwen2.5 72B Instruct: 38.9 (#188)

BenchmarkQwen1.5-72BQwen2.5 72B Instruct
LMArena Longer Query11571282

Writing & Preference Qwen2.5 72B Instruct leads

Qwen1.5-72B: 37.3 (#258), Qwen2.5 72B Instruct: 46.7 (#215)

BenchmarkQwen1.5-72BQwen2.5 72B Instruct
LMArena Text11661269
LMArena Creative Writing11371221
LMArena Multi-Turn11601272
WildBench—80.2%

Frequently asked questions

Is Qwen1.5-72B better than Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 30.8 on the Noometry Index.

Is Qwen1.5-72B or Qwen2.5 72B Instruct better for coding?

Qwen2.5 72B Instruct scores higher on coding benchmarks: 33.2 versus 31.9 in the Noometry coding category.

How many benchmarks do Qwen1.5-72B and Qwen2.5 72B Instruct share?

20 benchmarks have published results for both models. Qwen1.5-72B has 22 scored results on Noometry and Qwen2.5 72B Instruct has 43.

Related comparisons

Go deeper