Noometry

Model comparison

Qwen1.5-110B vs Qwen2.5 72B Instruct

Qwen1.5-110B is the stronger model overall, scoring 33.6 to 31.5 on the Noometry Index.

Last verified . 20 shared benchmarks.

Qwen1.5-110B Alibaba (Qwen)

33.6

Rank #231 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.5

Rank #259 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Qwen1.5-110B scores higher in 3 categories and Qwen2.5 72B Instruct in 5 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen1.5-110B leads 31.1 to 18.1.
  • The biggest single-benchmark swing is BigCodeBench Complete: 44.4% for Qwen1.5-110B and 55.9% for Qwen2.5 72B Instruct.

Side by side

Qwen1.5-110BQwen2.5 72B Instruct
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index33.631.5
Released2024-04-252024-09
WeightsOpenOpen
Context window—131K
Max output—8K
Input $ / M tokens—$1.40
Output $ / M tokens—$5.60
Results tracked2043

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

Category by category

Coding Too close to call

Qwen1.5-110B: 32.4 (#260), Qwen2.5 72B Instruct: 32.8 (#256)

BenchmarkQwen1.5-110BQwen2.5 72B Instruct
BigCodeBench Instruct35%45.8%
LMArena Coding11841293
BigCodeBench Complete44.4%55.9%
WeirdML—16%

Agentic & Tool Use Not comparable

Qwen1.5-110B: —, Qwen2.5 72B Instruct: 22.0 (#124)

BenchmarkQwen1.5-110BQwen2.5 72B Instruct
TheAgentCompany—5.7%
BALROG—16.2%
METR Time Horizons—35.8%

Reasoning Too close to call

Qwen1.5-110B: 21.7 (#192), Qwen2.5 72B Instruct: 21.4 (#197)

BenchmarkQwen1.5-110BQwen2.5 72B Instruct
LMArena Hard Prompts11681271
ForecastBench57.757.5
DTBench—62.9%
LMCA—13.4%
BIG-Bench Hard—79.8%
Epoch Capabilities Index—129.01
HellaSwag—84.8%
PIQA—82.6%
WinoGrande—82.3%

Math Qwen1.5-110B leads

Qwen1.5-110B: 31.1 (#199), Qwen2.5 72B Instruct: 18.1 (#281)

BenchmarkQwen1.5-110BQwen2.5 72B Instruct
LMArena Math11851283
OTIS Mock AIME 2024-2025—8.1%
Omni-MATH—33%
MATH Level 5—63.2%

Knowledge Qwen1.5-110B leads

Qwen1.5-110B: 30.7 (#217), Qwen2.5 72B Instruct: 26.9 (#247)

BenchmarkQwen1.5-110BQwen2.5 72B Instruct
LMArena Expert11441245
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

Qwen1.5-110B: 33.8 (#245), Qwen2.5 72B Instruct: 41.2 (#208)

BenchmarkQwen1.5-110BQwen2.5 72B Instruct
LMArena Non-English11421252
LMArena Chinese12061272
LMArena French11501279
LMArena German11231234
LMArena Japanese10741180
LMArena Korean10441188
LMArena Russian11181264
LMArena Spanish11411255

Instruction Following Qwen2.5 72B Instruct leads

Qwen1.5-110B: 60.6 (#247), Qwen2.5 72B Instruct: 65.7 (#216)

BenchmarkQwen1.5-110BQwen2.5 72B Instruct
LMArena Instruction Following11581254
IFEval—80.6%

Long Context Qwen2.5 72B Instruct leads

Qwen1.5-110B: 35.0 (#237), Qwen2.5 72B Instruct: 38.9 (#183)

BenchmarkQwen1.5-110BQwen2.5 72B Instruct
LMArena Longer Query11571282

Writing & Preference Qwen2.5 72B Instruct leads

Qwen1.5-110B: 38.1 (#250), Qwen2.5 72B Instruct: 46.9 (#210)

BenchmarkQwen1.5-110BQwen2.5 72B Instruct
LMArena Text11751269
LMArena Creative Writing11481221
LMArena Multi-Turn11601272
WildBench—80.2%

Frequently asked questions

Is Qwen1.5-110B better than Qwen2.5 72B Instruct?

Qwen1.5-110B is the stronger model overall, scoring 33.6 to 31.5 on the Noometry Index.

Is Qwen1.5-110B or Qwen2.5 72B Instruct better for coding?

They score almost the same on coding (32.4 vs 32.8); test both on your own repository before choosing.

How many benchmarks do Qwen1.5-110B and Qwen2.5 72B Instruct share?

20 benchmarks have published results for both models. Qwen1.5-110B has 20 scored results on Noometry and Qwen2.5 72B Instruct has 43.

Related comparisons

Go deeper