Noometry

Model comparison

Gemini 2.5 Pro vs Qwen2.5 72B Instruct

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 31.9 on the Noometry Index.

Last verified . 34 shared benchmarks.

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.9

Rank #267 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 9 categories and Qwen2.5 72B Instruct in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemini 2.5 Pro leads 56.0 to 27.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 84.7% for Gemini 2.5 Pro and 8.1% for Qwen2.5 72B Instruct.
  • Qwen2.5 72B Instruct is cheaper at $1.40 / $5.60 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 131K.
  • Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.

Side by side

Gemini 2.5 ProQwen2.5 72B Instruct
ProviderGoogleAlibaba (Qwen)
Noometry Index45.031.9
Released2025-03-252024-09
WeightsProprietaryOpen
Context window1.05M131K
Max output66K8K
Input $ / M tokens$1.25$1.40
Output $ / M tokens$10$5.60
Results tracked7843

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 72B Instruct: 33.2 (#260)

BenchmarkGemini 2.5 ProQwen2.5 72B Instruct
WeirdML54%16%
LMArena Coding14521292
SWE-bench Verified57.6%—
SWE-bench Verified (bash only)53.6%—
Aider Polyglot83.1%—
LMArena WebDev1227—
SciCode42.8%—
GSO3.9%—
BigCodeBench Instruct—45.8%
LiveBench Coding85.9%—
BigCodeBench Complete—55.9%
CadEval64%—
ALE-Bench785.52—
AlgoTune1.51—

Agentic & Tool Use Gemini 2.5 Pro leads

Gemini 2.5 Pro: 29.2 (#88), Qwen2.5 72B Instruct: 22.1 (#133)

BenchmarkGemini 2.5 ProQwen2.5 72B Instruct
TheAgentCompany30.3%5.7%
BALROG43.3%16.2%
METR Time Horizons55.4%35.8%
Terminal-Bench32.6%—
GDPval23.3%—
Remote Labor Index0.8%—
τ²-bench Banking13.7%—
DeepResearch Bench42.8%—
LMArena Search1142—
Vending-Bench 2573.64—

Reasoning Gemini 2.5 Pro leads

Gemini 2.5 Pro: 28.8 (#99), Qwen2.5 72B Instruct: 22.3 (#199)

BenchmarkGemini 2.5 ProQwen2.5 72B Instruct
LMArena Hard Prompts14551271
DTBench82.4%62.9%
LMCA34.8%13.4%
Epoch Capabilities Index145.32129
ForecastBench61.357.5
ARC-AGI-24.9%—
SimpleBench62.4%—
Kagi LLM Benchmark70.3%—
ARC-AGI-141%—
CritPt2%—
Chess Puzzles20%—
EnigmaEval5.6%—
LiveBench Reasoning89.8%—
LiveBench Data Analysis79.9%—
BIG-Bench Hard—79.8%
HellaSwag—84.8%
LiveBench82.3%—
PIQA—82.6%
WinoGrande—82.3%

Math Gemini 2.5 Pro leads

Gemini 2.5 Pro: 32.5 (#213), Qwen2.5 72B Instruct: 19.3 (#287)

BenchmarkGemini 2.5 ProQwen2.5 72B Instruct
OTIS Mock AIME 2024-202584.7%8.1%
Omni-MATH41.6%33%
LMArena Math14501283
MATH Level 595.9%63.2%
FrontierMath (Tiers 1-3)24.6%—
FrontierMath Tier 40%—
LiveBench Math90.2%—
FrontierMath (Feb 2025 set)14.1%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Gemini 2.5 Pro leads

Gemini 2.5 Pro: 56.0 (#46), Qwen2.5 72B Instruct: 27.0 (#253)

BenchmarkGemini 2.5 ProQwen2.5 72B Instruct
GPQA Diamond85.3%49.1%
MMLU-Pro86.3%63.1%
Confabulations10.6%19.1%
GPQA (HELM)74.9%42.6%
LMArena Expert14521245
Humanity's Last Exam21.6%—
Vectara Hallucination Rate7%—
ARC (AI2) Challenge—94.5%
MMLU—85.3%
TriviaQA—71.9%

Multimodal Not comparable

Gemini 2.5 Pro: 45.2 (#18), Qwen2.5 72B Instruct: —

BenchmarkGemini 2.5 ProQwen2.5 72B Instruct
LMArena Vision1263—
GeoBench86%—
VPCT48%—
LMArena Document1421—
SpatialViz-Bench44.7%—

Multilingual Gemini 2.5 Pro leads

Gemini 2.5 Pro: 55.3 (#31), Qwen2.5 72B Instruct: 41.0 (#213)

BenchmarkGemini 2.5 ProQwen2.5 72B Instruct
LMArena Non-English14511252
LMArena Chinese15071272
LMArena French14721280
LMArena German14871234
LMArena Japanese14611180
LMArena Korean14341188
LMArena Russian14611264
LMArena Spanish14731256

Instruction Following Gemini 2.5 Pro leads

Gemini 2.5 Pro: 75.0 (#75), Qwen2.5 72B Instruct: 65.5 (#221)

BenchmarkGemini 2.5 ProQwen2.5 72B Instruct
IFEval84%80.6%
LMArena Instruction Following14371254
LiveBench Instruction Following80.6%—

Long Context Gemini 2.5 Pro leads

Gemini 2.5 Pro: 59.8 (#5), Qwen2.5 72B Instruct: 38.9 (#188)

BenchmarkGemini 2.5 ProQwen2.5 72B Instruct
LMArena Longer Query14491282
Fiction.LiveBench91.7%—

Writing & Preference Gemini 2.5 Pro leads

Gemini 2.5 Pro: 63.7 (#62), Qwen2.5 72B Instruct: 46.7 (#215)

BenchmarkGemini 2.5 ProQwen2.5 72B Instruct
LMArena Text14581269
LMArena Creative Writing14541221
WildBench85.7%80.2%
LMArena Multi-Turn14531272
Short-Story Creative Writing83.8%—
EQ-Bench Creative Writing1421—
LiveBench Language67.8%—

Frequently asked questions

Is Gemini 2.5 Pro better than Qwen2.5 72B Instruct?

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 31.9 on the Noometry Index.

Which is cheaper, Gemini 2.5 Pro or Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is cheaper. It lists at $1.40 per million input tokens and $5.60 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

Is Gemini 2.5 Pro or Qwen2.5 72B Instruct better for coding?

Gemini 2.5 Pro scores higher on coding benchmarks: 42.4 versus 33.2 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 131K.

How many benchmarks do Gemini 2.5 Pro and Qwen2.5 72B Instruct share?

34 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Qwen2.5 72B Instruct has 43.

Related comparisons

Go deeper