Noometry

Model comparison

Gemini 2.5 Pro vs Qwen2.5-Coder-32B

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 33.4 on the Noometry Index. Qwen2.5-Coder-32B costs 4.6× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

Last verified . 22 shared benchmarks.

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

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

33.4

Rank #245 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 7 categories and Qwen2.5-Coder-32B in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemini 2.5 Pro leads 56.0 to 33.4.
  • The biggest single-benchmark swing is Aider Polyglot: 83.1% for Gemini 2.5 Pro and 16.4% for Qwen2.5-Coder-32B.
  • Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
  • Gemini 2.5 Pro accepts more context: 1.05M tokens versus 33K.
  • Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.

Side by side

Gemini 2.5 ProQwen2.5-Coder-32B
ProviderGoogleAlibaba (Qwen)
Noometry Index45.033.4
Released2025-03-252024-09-18
WeightsProprietaryOpen
Context window1.05M33K
Max output66K29K
Input $ / M tokens$1.25$0.66
Output $ / M tokens$10$1
Results tracked7831

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

Category by category

Coding Gemini 2.5 Pro leads

Gemini 2.5 Pro: 42.4 (#101), Qwen2.5-Coder-32B: 22.6 (#333)

BenchmarkGemini 2.5 ProQwen2.5-Coder-32B
SWE-bench Verified (bash only)53.6%9%
Aider Polyglot83.1%16.4%
LiveBench Coding85.9%56.9%
LMArena Coding14521276
SWE-bench Verified57.6%—
LMArena WebDev1227—
SciCode42.8%—
GSO3.9%—
WeirdML54%—
BigCodeBench Instruct—49%
BigCodeBench Complete—58%
CadEval64%—
ALE-Bench785.52—
AlgoTune1.51—
HumanEval+—87.2%
MBPP+—77%

Agentic & Tool Use Not comparable

Gemini 2.5 Pro: 29.2 (#88), Qwen2.5-Coder-32B: —

BenchmarkGemini 2.5 ProQwen2.5-Coder-32B
Terminal-Bench32.6%—
GDPval23.3%—
Remote Labor Index0.8%—
TheAgentCompany30.3%—
τ²-bench Banking13.7%—
DeepResearch Bench42.8%—
BALROG43.3%—
LMArena Search1142—
METR Time Horizons55.4%—
Vending-Bench 2573.64—

Reasoning Gemini 2.5 Pro leads

Gemini 2.5 Pro: 28.8 (#99), Qwen2.5-Coder-32B: 21.2 (#225)

BenchmarkGemini 2.5 ProQwen2.5-Coder-32B
LiveBench Reasoning89.8%42.1%
LMArena Hard Prompts14551251
LiveBench Data Analysis79.9%49.9%
Epoch Capabilities Index145.32119.49
LiveBench82.3%46.2%
ARC-AGI-24.9%—
SimpleBench62.4%—
Kagi LLM Benchmark70.3%—
ARC-AGI-141%—
CritPt2%—
Chess Puzzles20%—
EnigmaEval5.6%—
DTBench82.4%—
LMCA34.8%—
ForecastBench61.3—
HellaSwag—83%
WinoGrande—80.8%

Math Too close to call

Gemini 2.5 Pro: 32.5 (#213), Qwen2.5-Coder-32B: 33.3 (#204)

BenchmarkGemini 2.5 ProQwen2.5-Coder-32B
LiveBench Math90.2%46.6%
LMArena Math14501251
FrontierMath (Tiers 1-3)24.6%—
FrontierMath Tier 40%—
OTIS Mock AIME 2024-202584.7%—
Omni-MATH41.6%—
MATH Level 595.9%—
FrontierMath (Feb 2025 set)14.1%—
FrontierMath Tier 4 (v1)4.2%—
GSM8K—93%

Knowledge Gemini 2.5 Pro leads

Gemini 2.5 Pro: 56.0 (#46), Qwen2.5-Coder-32B: 33.4 (#203)

BenchmarkGemini 2.5 ProQwen2.5-Coder-32B
LMArena Expert14521221
GPQA Diamond85.3%—
Humanity's Last Exam21.6%—
MMLU-Pro86.3%—
Confabulations10.6%—
Vectara Hallucination Rate7%—
GPQA (HELM)74.9%—
ARC (AI2) Challenge—70.5%
MMLU—79.1%

Multimodal Not comparable

Gemini 2.5 Pro: 45.2 (#18), Qwen2.5-Coder-32B: —

BenchmarkGemini 2.5 ProQwen2.5-Coder-32B
LMArena Vision1263—
GeoBench86%—
VPCT48%—
LMArena Document1421—
SpatialViz-Bench44.7%—

Multilingual Gemini 2.5 Pro leads

Gemini 2.5 Pro: 55.3 (#31), Qwen2.5-Coder-32B: 37.8 (#235)

BenchmarkGemini 2.5 ProQwen2.5-Coder-32B
LMArena Non-English14511205
LMArena Chinese15071222
LMArena Russian14611228
LMArena French1472—
LMArena German1487—
LMArena Japanese1461—
LMArena Korean1434—
LMArena Spanish1473—

Instruction Following Gemini 2.5 Pro leads

Gemini 2.5 Pro: 75.0 (#75), Qwen2.5-Coder-32B: 61.4 (#245)

BenchmarkGemini 2.5 ProQwen2.5-Coder-32B
LiveBench Instruction Following80.6%58.7%
LMArena Instruction Following14371223
IFEval84%—

Long Context Gemini 2.5 Pro leads

Gemini 2.5 Pro: 59.8 (#5), Qwen2.5-Coder-32B: 38.0 (#208)

BenchmarkGemini 2.5 ProQwen2.5-Coder-32B
LMArena Longer Query14491251
Fiction.LiveBench91.7%—

Writing & Preference Gemini 2.5 Pro leads

Gemini 2.5 Pro: 63.7 (#62), Qwen2.5-Coder-32B: 41.6 (#240)

BenchmarkGemini 2.5 ProQwen2.5-Coder-32B
LMArena Text14581230
LMArena Creative Writing14541174
LMArena Multi-Turn14531222
LiveBench Language67.8%23.3%
Short-Story Creative Writing83.8%—
EQ-Bench Creative Writing1421—
WildBench85.7%—

Frequently asked questions

Is Gemini 2.5 Pro better than Qwen2.5-Coder-32B?

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 33.4 on the Noometry Index. Qwen2.5-Coder-32B costs 4.6× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

Which is cheaper, Gemini 2.5 Pro or Qwen2.5-Coder-32B?

Qwen2.5-Coder-32B is cheaper. It lists at $0.66 per million input tokens and $1 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

Is Gemini 2.5 Pro or Qwen2.5-Coder-32B better for coding?

Gemini 2.5 Pro scores higher on coding benchmarks: 42.4 versus 22.6 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 33K.

How many benchmarks do Gemini 2.5 Pro and Qwen2.5-Coder-32B share?

22 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Qwen2.5-Coder-32B has 31.

Related comparisons

Go deeper