Noometry

Model comparison

Gemini 3 Flash Preview vs GPT-4o mini

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 25.4 on the Noometry Index. GPT-4o mini costs 4.3× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.

Last verified . 33 shared benchmarks.

Gemini 3 Flash Preview Google

52.3

Rank #33 Confirmed

GPT-4o mini OpenAI

25.4

Rank #337 Confirmed

Summary

  • They share 33 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 10 categories and GPT-4o mini in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemini 3 Flash Preview leads 51.4 to 9.9.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3 Flash Preview and 6.9% for GPT-4o mini.
  • GPT-4o mini is cheaper at $0.15 / $0.60 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 128K.

Side by side

Gemini 3 Flash PreviewGPT-4o mini
ProviderGoogleOpenAI
Noometry Index52.325.4
Released2025-12-172024-07-18
WeightsProprietaryProprietary
Context window1.05M128K
Max output66K16K
Input $ / M tokens$0.50$0.15
Output $ / M tokens$3$0.60
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-4o mini: 21.6 (#330)

BenchmarkGemini 3 Flash PreviewGPT-4o mini
WeirdML61.6%11.8%
LMArena Coding14601290
SWE-bench Verified75.4%—
SWE-bench Verified (bash only)75.8%—
Aider Polyglot—3.6%
LMArena WebDev1439—
SWE-bench Multilingual72.7%—
GSO9.8%—
BigCodeBench Instruct—46.1%
LiveBench Coding—43.1%
BigCodeBench Complete—57.4%
ALE-Bench1,367—
HumanEval+—83.5%
MBPP+—72.2%

Agentic & Tool Use Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 38.6 (#27), GPT-4o mini: 27.2 (#95)

BenchmarkGemini 3 Flash PreviewGPT-4o mini
BALROG48.1%17.4%
Terminal-Bench64.3%—
τ²-bench Airline82.5%—
τ²-bench Banking27.3%—
τ²-bench Retail76.8%—
τ²-bench Telecom91.2%—
DeepResearch Bench49.8%—
GDP.pdf10%—
LMArena Search1198—
Vending-Bench 23,635—

Reasoning Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 49.2 (#35), GPT-4o mini: 8.7 (#343)

BenchmarkGemini 3 Flash PreviewGPT-4o mini
ARC-AGI-233.6%0%
SimpleBench61.1%10.7%
Chess Puzzles40%0%
LMArena Hard Prompts14651267
Mystery Game Puzzles26%12%
DTBench89.1%54.4%
LMCA43.1%10.4%
Epoch Capabilities Index151.83126.56
Kagi LLM Benchmark—28.8%
NYT Connections (extended)83.1%—
ARC-AGI-184.7%—
LiveBench Reasoning—32.8%
LiveBench Data Analysis—50%
ForecastBench58.5—
LiveBench—41.3%
PIQA—88.7%

Math Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 51.4 (#42), GPT-4o mini: 9.9 (#307)

BenchmarkGemini 3 Flash PreviewGPT-4o mini
FrontierMath (Tiers 1-3)51.2%0.7%
OTIS Mock AIME 2024-202595.6%6.9%
LMArena Math14721267
FrontierMath Tier 417.1%—
MathArena Final-Answer Competitions67.6%—
ProofBench15%—
Omni-MATH—28%
LiveBench Math—36.3%
MATH Level 5—52.6%
FrontierMath (Feb 2025 set)35.6%—
FrontierMath Tier 4 (v1)4.2%—
GSM8K—91.3%

Knowledge Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 58.8 (#30), GPT-4o mini: 17.7 (#279)

BenchmarkGemini 3 Flash PreviewGPT-4o mini
GPQA Diamond89.4%37.7%
SimpleQA Verified66.8%8.3%
LMArena Expert14611235
MMLU-Pro—60.3%
Confabulations—37.2%
Vectara Hallucination Rate13.5%—
GPQA (HELM)—36.8%
BoolQ—88.7%
MMLU—81.8%

Multimodal Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 45.3 (#15), GPT-4o mini: 25.3 (#117)

BenchmarkGemini 3 Flash PreviewGPT-4o mini
LMArena Vision12851066
GeoBench88%64%
VPCT72.6%34%
Video-MME—64.8%
Blueprint-Bench 20%—
LMArena Document1413—

Multilingual Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 55.9 (#26), GPT-4o mini: 42.2 (#194)

BenchmarkGemini 3 Flash PreviewGPT-4o mini
LMArena Non-English14581266
LMArena Chinese15101264
LMArena French14781296
LMArena German14971272
LMArena Japanese14881216
LMArena Korean14431195
LMArena Russian14801275
LMArena Spanish14701276

Instruction Following Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 75.8 (#52), GPT-4o mini: 62.1 (#234)

BenchmarkGemini 3 Flash PreviewGPT-4o mini
LMArena Instruction Following14371259
LiveBench Instruction Following—56.8%
IFEval—78.2%

Long Context Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 44.4 (#63), GPT-4o mini: 39.1 (#181)

BenchmarkGemini 3 Flash PreviewGPT-4o mini
LMArena Longer Query14521289

Writing & Preference Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 65.6 (#44), GPT-4o mini: 39.7 (#243)

BenchmarkGemini 3 Flash PreviewGPT-4o mini
LMArena Text14661286
LMArena Creative Writing14571268
LMArena Multi-Turn14711285
Short-Story Creative Writing—67.2%
EQ-Bench Creative Writing—873
WildBench—79.1%
LiveBench Language—28.6%

Frequently asked questions

Is Gemini 3 Flash Preview better than GPT-4o mini?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 25.4 on the Noometry Index. GPT-4o mini costs 4.3× 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-4o mini?

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Gemini 3 Flash Preview lists at $0.50 and $3.

Is Gemini 3 Flash Preview or GPT-4o mini better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 51.5 versus 21.6 in the Noometry coding category.

Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 128K.

How many benchmarks do Gemini 3 Flash Preview and GPT-4o mini share?

33 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and GPT-4o mini has 60.

Related comparisons

Go deeper