Noometry

Model comparison

Qwen1.5-110B vs Qwen2.5-Coder-32B

Qwen1.5-110B and Qwen2.5-Coder-32B score almost the same on the Noometry Index (34.2 vs 33.4), so choose on price, context window or the category you care about most.

Last verified . 14 shared benchmarks.

Qwen1.5-110B Alibaba (Qwen)

34.2

Rank #234 Confirmed

Qwen2.5-Coder-32B Alibaba (Qwen)

33.4

Rank #245 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Qwen1.5-110B scores higher in 3 categories and Qwen2.5-Coder-32B in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Qwen1.5-110B leads 33.0 to 22.6.
  • The biggest single-benchmark swing is BigCodeBench Instruct: 35% for Qwen1.5-110B and 49% for Qwen2.5-Coder-32B.

Side by side

Qwen1.5-110BQwen2.5-Coder-32B
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index34.233.4
Released2024-04-252024-09-18
WeightsOpenOpen
Context window—33K
Max output—29K
Input $ / M tokens—$0.66
Output $ / M tokens—$1
Results tracked2031

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

Category by category

Coding Qwen1.5-110B leads

Qwen1.5-110B: 33.0 (#264), Qwen2.5-Coder-32B: 22.6 (#333)

BenchmarkQwen1.5-110BQwen2.5-Coder-32B
BigCodeBench Instruct35%49%
LMArena Coding11841276
BigCodeBench Complete44.4%58%
SWE-bench Verified (bash only)—9%
Aider Polyglot—16.4%
LiveBench Coding—56.9%
HumanEval+—87.2%
MBPP+—77%

Reasoning Qwen1.5-110B leads

Qwen1.5-110B: 22.7 (#189), Qwen2.5-Coder-32B: 21.2 (#225)

BenchmarkQwen1.5-110BQwen2.5-Coder-32B
LMArena Hard Prompts11681251
LiveBench Reasoning—42.1%
LiveBench Data Analysis—49.9%
Epoch Capabilities Index—119.49
ForecastBench57.7—
HellaSwag—83%
LiveBench—46.2%
WinoGrande—80.8%

Math Too close to call

Qwen1.5-110B: 33.7 (#201), Qwen2.5-Coder-32B: 33.3 (#204)

BenchmarkQwen1.5-110BQwen2.5-Coder-32B
LMArena Math11851251
LiveBench Math—46.6%
GSM8K—93%

Knowledge Qwen2.5-Coder-32B leads

Qwen1.5-110B: 31.2 (#219), Qwen2.5-Coder-32B: 33.4 (#203)

BenchmarkQwen1.5-110BQwen2.5-Coder-32B
LMArena Expert11441221
ARC (AI2) Challenge—70.5%
MMLU—79.1%

Multilingual Qwen2.5-Coder-32B leads

Qwen1.5-110B: 33.6 (#250), Qwen2.5-Coder-32B: 37.8 (#235)

BenchmarkQwen1.5-110BQwen2.5-Coder-32B
LMArena Non-English11421205
LMArena Chinese12061222
LMArena Russian11181228
LMArena French1151—
LMArena German1123—
LMArena Japanese1074—
LMArena Korean1044—
LMArena Spanish1142—

Instruction Following Qwen2.5-Coder-32B leads

Qwen1.5-110B: 60.3 (#252), Qwen2.5-Coder-32B: 61.4 (#245)

BenchmarkQwen1.5-110BQwen2.5-Coder-32B
LMArena Instruction Following11581223
LiveBench Instruction Following—58.7%

Long Context Qwen2.5-Coder-32B leads

Qwen1.5-110B: 35.1 (#242), Qwen2.5-Coder-32B: 38.0 (#208)

BenchmarkQwen1.5-110BQwen2.5-Coder-32B
LMArena Longer Query11571251

Writing & Preference Qwen2.5-Coder-32B leads

Qwen1.5-110B: 38.0 (#255), Qwen2.5-Coder-32B: 41.6 (#240)

BenchmarkQwen1.5-110BQwen2.5-Coder-32B
LMArena Text11751230
LMArena Creative Writing11481174
LMArena Multi-Turn11601222
LiveBench Language—23.3%

Frequently asked questions

Is Qwen1.5-110B better than Qwen2.5-Coder-32B?

Qwen1.5-110B and Qwen2.5-Coder-32B score almost the same on the Noometry Index (34.2 vs 33.4), so choose on price, context window or the category you care about most.

Is Qwen1.5-110B or Qwen2.5-Coder-32B better for coding?

Qwen1.5-110B scores higher on coding benchmarks: 33.0 versus 22.6 in the Noometry coding category.

How many benchmarks do Qwen1.5-110B and Qwen2.5-Coder-32B share?

14 benchmarks have published results for both models. Qwen1.5-110B has 20 scored results on Noometry and Qwen2.5-Coder-32B has 31.

Related comparisons

Go deeper