Noometry

Model comparison

Gemini 3 Flash Preview vs GPT-5 Mini

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 41.7 on the Noometry Index. GPT-5 Mini costs 1.6× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.

Last verified . 43 shared benchmarks.

Gemini 3 Flash Preview Google

52.3

Rank #33 Confirmed

GPT-5 Mini OpenAI

41.7

Rank #115 Confirmed

Summary

  • They share 43 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 9 categories and GPT-5 Mini in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 24.1.
  • The biggest single-benchmark swing is SimpleQA Verified: 66.8% for Gemini 3 Flash Preview and 21.6% for GPT-5 Mini.
  • GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $0.50 / $3 for Gemini 3 Flash Preview.
  • Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 400K.

Side by side

Gemini 3 Flash PreviewGPT-5 Mini
ProviderGoogleOpenAI
Noometry Index52.341.7
Released2025-12-172025-08-07
WeightsProprietaryProprietary
Context window1.05M400K
Max output66K128K
Input $ / M tokens$0.50$0.25
Output $ / M tokens$3$2
Results tracked5960

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), GPT-5 Mini: 40.0 (#134)

BenchmarkGemini 3 Flash PreviewGPT-5 Mini
SWE-bench Verified75.4%64.7%
SWE-bench Verified (bash only)75.8%59.8%
SWE-bench Multilingual72.7%39.7%
WeirdML61.6%52.7%
LMArena Coding14601406
ALE-Bench1,367799.77
LMArena WebDev1439—
SciCode—39.2%
GSO9.8%—
AlgoTune—1.38

Agentic & Tool Use Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 38.6 (#27), GPT-5 Mini: 31.0 (#64)

BenchmarkGemini 3 Flash PreviewGPT-5 Mini
Terminal-Bench64.3%34.8%
Vending-Bench 23,635-31.18
Berkeley Function Calling Leaderboard—55.5%
τ²-bench Airline82.5%—
τ²-bench Banking27.3%—
τ²-bench Retail76.8%—
τ²-bench Telecom91.2%—
DeepResearch Bench49.8%—
BALROG48.1%—
GDP.pdf10%—
LMArena Search1198—

Reasoning Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 49.2 (#35), GPT-5 Mini: 24.1 (#153)

BenchmarkGemini 3 Flash PreviewGPT-5 Mini
ARC-AGI-233.6%4.4%
ARC-AGI-184.7%54.3%
Chess Puzzles40%30%
LMArena Hard Prompts14651380
Mystery Game Puzzles26%10%
DTBench89.1%80.5%
LMCA43.1%34.2%
Epoch Capabilities Index151.83145.51
ForecastBench58.561
SimpleBench61.1%—
Kagi LLM Benchmark—70.3%
NYT Connections (extended)83.1%—
CritPt—0%
EnigmaEval—8.2%

Math Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 51.4 (#42), GPT-5 Mini: 46.3 (#59)

BenchmarkGemini 3 Flash PreviewGPT-5 Mini
FrontierMath (Tiers 1-3)51.2%46.7%
FrontierMath Tier 417.1%12.2%
OTIS Mock AIME 2024-202595.6%86.7%
ProofBench15%9%
LMArena Math14721377
FrontierMath (Feb 2025 set)35.6%27.2%
FrontierMath Tier 4 (v1)4.2%6.3%
MathArena Final-Answer Competitions67.6%—
Omni-MATH—72.2%
MATH Level 5—97.8%

Knowledge Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 58.8 (#30), GPT-5 Mini: 45.5 (#80)

BenchmarkGemini 3 Flash PreviewGPT-5 Mini
GPQA Diamond89.4%75%
SimpleQA Verified66.8%21.6%
Vectara Hallucination Rate13.5%12.9%
LMArena Expert14611377
Humanity's Last Exam—19.4%
MMLU-Pro—83.5%
Confabulations—13.3%
GPQA (HELM)—75.6%

Multimodal Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 45.3 (#15), GPT-5 Mini: 35.0 (#80)

BenchmarkGemini 3 Flash PreviewGPT-5 Mini
LMArena Vision12851202
VPCT72.6%40.2%
GeoBench88%—
Blueprint-Bench 20%—
LMArena Document1413—

Multilingual Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 55.9 (#26), GPT-5 Mini: 49.1 (#131)

BenchmarkGemini 3 Flash PreviewGPT-5 Mini
LMArena Non-English14581363
LMArena Chinese15101387
LMArena French14781385
LMArena German14971366
LMArena Japanese14881342
LMArena Korean14431306
LMArena Russian14801362
LMArena Spanish14701355

Instruction Following Too close to call

Gemini 3 Flash Preview: 75.8 (#52), GPT-5 Mini: 76.4 (#43)

BenchmarkGemini 3 Flash PreviewGPT-5 Mini
LMArena Instruction Following14371357
IFEval—92.7%

Long Context Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 44.4 (#63), GPT-5 Mini: 41.9 (#127)

BenchmarkGemini 3 Flash PreviewGPT-5 Mini
LMArena Longer Query14521355
Fiction.LiveBench—69.4%

Writing & Preference Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 65.6 (#44), GPT-5 Mini: 55.4 (#143)

BenchmarkGemini 3 Flash PreviewGPT-5 Mini
LMArena Text14661373
LMArena Creative Writing14571325
LMArena Multi-Turn14711363
Short-Story Creative Writing—83.1%
EQ-Bench Creative Writing—1313
WildBench—85.5%

Frequently asked questions

Is Gemini 3 Flash Preview better than GPT-5 Mini?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 41.7 on the Noometry Index. GPT-5 Mini costs 1.6× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.

Which is cheaper, Gemini 3 Flash Preview or GPT-5 Mini?

GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Gemini 3 Flash Preview lists at $0.50 and $3.

Is Gemini 3 Flash Preview or GPT-5 Mini better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 51.5 versus 40.0 in the Noometry coding category.

Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 400K.

How many benchmarks do Gemini 3 Flash Preview and GPT-5 Mini share?

43 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and GPT-5 Mini has 60.

Related comparisons

Go deeper