Noometry

Model comparison

Gemini 3 Flash Preview vs Qwen2.5 72B Instruct

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 31.5 on the Noometry Index.

Last verified . 25 shared benchmarks.

Gemini 3 Flash Preview Google

52.3

Rank #33 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.5

Rank #259 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Gemini 3 Flash Preview 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 math, where Gemini 3 Flash Preview leads 51.4 to 18.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3 Flash Preview and 8.1% for Qwen2.5 72B Instruct.
  • Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
  • Gemini 3 Flash Preview 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 3 Flash PreviewQwen2.5 72B Instruct
ProviderGoogleAlibaba (Qwen)
Noometry Index52.331.5
Released2025-12-172024-09
WeightsProprietaryOpen
Context window1.05M131K
Max output66K8K
Input $ / M tokens$0.50$1.40
Output $ / M tokens$3$5.60
Results tracked5943

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

Category by category

Coding Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 51.5 (#35), Qwen2.5 72B Instruct: 32.8 (#256)

BenchmarkGemini 3 Flash PreviewQwen2.5 72B Instruct
WeirdML61.6%16%
LMArena Coding14601293
SWE-bench Verified75.4%—
SWE-bench Verified (bash only)75.8%—
LMArena WebDev1439—
SWE-bench Multilingual72.7%—
GSO9.8%—
BigCodeBench Instruct—45.8%
BigCodeBench Complete—55.9%
ALE-Bench1,367—

Agentic & Tool Use Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 38.6 (#27), Qwen2.5 72B Instruct: 22.0 (#124)

BenchmarkGemini 3 Flash PreviewQwen2.5 72B Instruct
BALROG48.1%16.2%
Terminal-Bench64.3%—
TheAgentCompany—5.7%
τ²-bench Airline82.5%—
τ²-bench Banking27.3%—
τ²-bench Retail76.8%—
τ²-bench Telecom91.2%—
DeepResearch Bench49.8%—
GDP.pdf10%—
LMArena Search1198—
METR Time Horizons—35.8%
Vending-Bench 23,635—

Reasoning Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 49.2 (#35), Qwen2.5 72B Instruct: 21.4 (#197)

BenchmarkGemini 3 Flash PreviewQwen2.5 72B Instruct
LMArena Hard Prompts14651271
DTBench89.1%62.9%
LMCA43.1%13.4%
Epoch Capabilities Index151.83129.01
ForecastBench58.557.5
ARC-AGI-233.6%—
SimpleBench61.1%—
NYT Connections (extended)83.1%—
ARC-AGI-184.7%—
Chess Puzzles40%—
Mystery Game Puzzles26%—
BIG-Bench Hard—79.8%
HellaSwag—84.8%
PIQA—82.6%
WinoGrande—82.3%

Math Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 51.4 (#42), Qwen2.5 72B Instruct: 18.1 (#281)

BenchmarkGemini 3 Flash PreviewQwen2.5 72B Instruct
OTIS Mock AIME 2024-202595.6%8.1%
LMArena Math14721283
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 417.1%—
MathArena Final-Answer Competitions67.6%—
ProofBench15%—
Omni-MATH—33%
MATH Level 5—63.2%
FrontierMath (Feb 2025 set)35.6%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 58.8 (#30), Qwen2.5 72B Instruct: 26.9 (#247)

BenchmarkGemini 3 Flash PreviewQwen2.5 72B Instruct
GPQA Diamond89.4%49.1%
LMArena Expert14611245
SimpleQA Verified66.8%—
MMLU-Pro—63.1%
Confabulations—19.1%
Vectara Hallucination Rate13.5%—
GPQA (HELM)—42.6%
ARC (AI2) Challenge—94.5%
MMLU—85.3%
TriviaQA—71.9%

Multimodal Not comparable

Gemini 3 Flash Preview: 45.3 (#15), Qwen2.5 72B Instruct: —

BenchmarkGemini 3 Flash PreviewQwen2.5 72B Instruct
LMArena Vision1285—
GeoBench88%—
VPCT72.6%—
Blueprint-Bench 20%—
LMArena Document1413—

Multilingual Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 55.9 (#26), Qwen2.5 72B Instruct: 41.2 (#208)

BenchmarkGemini 3 Flash PreviewQwen2.5 72B Instruct
LMArena Non-English14581252
LMArena Chinese15101272
LMArena French14781279
LMArena German14971234
LMArena Japanese14881180
LMArena Korean14431188
LMArena Russian14801264
LMArena Spanish14701255

Instruction Following Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 75.8 (#52), Qwen2.5 72B Instruct: 65.7 (#216)

BenchmarkGemini 3 Flash PreviewQwen2.5 72B Instruct
LMArena Instruction Following14371254
IFEval—80.6%

Long Context Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 44.4 (#63), Qwen2.5 72B Instruct: 38.9 (#183)

BenchmarkGemini 3 Flash PreviewQwen2.5 72B Instruct
LMArena Longer Query14521282

Writing & Preference Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 65.6 (#44), Qwen2.5 72B Instruct: 46.9 (#210)

BenchmarkGemini 3 Flash PreviewQwen2.5 72B Instruct
LMArena Text14661269
LMArena Creative Writing14571221
LMArena Multi-Turn14711272
WildBench—80.2%

Frequently asked questions

Is Gemini 3 Flash Preview better than Qwen2.5 72B Instruct?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 31.5 on the Noometry Index.

Which is cheaper, Gemini 3 Flash Preview or Qwen2.5 72B Instruct?

Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.

Is Gemini 3 Flash Preview or Qwen2.5 72B Instruct better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 51.5 versus 32.8 in the Noometry coding category.

Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 131K.

How many benchmarks do Gemini 3 Flash Preview and Qwen2.5 72B Instruct share?

25 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Qwen2.5 72B Instruct has 43.

Related comparisons

Go deeper