Noometry

Model comparison

Gemini 3 Flash Preview vs GPT-5

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 50.9 on the Noometry Index.

Last verified . 48 shared benchmarks.

Gemini 3 Flash Preview Google

52.3

Rank #40 Confirmed

GPT-5 OpenAI

50.9

Rank #45 Confirmed

Summary

  • They share 48 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 7 categories and GPT-5 in 3 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in long context, where GPT-5 leads 69.5 to 44.4.
  • The biggest single-benchmark swing is ARC-AGI-2: 33.6% for Gemini 3 Flash Preview and 9.9% for GPT-5.
  • Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $1.25 / $10 for GPT-5.
  • Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 400K.

Side by side

Gemini 3 Flash PreviewGPT-5
ProviderGoogleOpenAI
Noometry Index52.350.9
Released2025-12-172025-08-07
WeightsProprietaryProprietary
Context window1.05M400K
Max output66K128K
Input $ / M tokens$0.50$1.25
Output $ / M tokens$3$10
Results tracked5969

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

Category by category

Coding Too close to call

Gemini 3 Flash Preview: 50.9 (#42), GPT-5: 50.3 (#47)

BenchmarkGemini 3 Flash PreviewGPT-5
SWE-bench Verified75.4%73.6%
SWE-bench Verified (bash only)75.8%65%
LMArena WebDev14391418
GSO9.8%6.9%
WeirdML61.6%60.7%
LMArena Coding14601436
ALE-Bench1,3671,162
Aider Polyglot—88%
SWE-bench Multilingual72.7%—
SciCode—42.9%
AlgoTune—1.67

Agentic & Tool Use Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 38.7 (#29), GPT-5: 33.1 (#56)

BenchmarkGemini 3 Flash PreviewGPT-5
Terminal-Bench64.3%49.6%
DeepResearch Bench49.8%49.6%
BALROG48.1%32.8%
LMArena Search11981133
GDPval—34.8%
Remote Labor Index—1.7%
τ²-bench Airline82.5%—
τ²-bench Banking27.3%—
τ²-bench Retail76.8%—
τ²-bench Telecom91.2%—
GDP.pdf10%—
METR Time Horizons—69.6%
Vending-Bench 23,635—

Reasoning Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 49.2 (#37), GPT-5: 38.3 (#64)

BenchmarkGemini 3 Flash PreviewGPT-5
ARC-AGI-233.6%9.9%
SimpleBench61.1%56.7%
ARC-AGI-184.7%65.7%
Chess Puzzles40%37%
LMArena Hard Prompts14651416
Mystery Game Puzzles26%23%
DTBench89.1%90.7%
LMCA43.1%40%
Epoch Capabilities Index151.8150
ForecastBench58.561.4
Kagi LLM Benchmark—72.7%
NYT Connections (extended)83.1%—
CritPt—12.6%
EnigmaEval—10.5%
EBR-Bench—12.7%

Math GPT-5 leads

Gemini 3 Flash Preview: 51.7 (#55), GPT-5: 55.0 (#44)

BenchmarkGemini 3 Flash PreviewGPT-5
FrontierMath (Tiers 1-3)51.2%55.4%
FrontierMath Tier 417.1%22%
OTIS Mock AIME 2024-202595.6%91.4%
ProofBench15%18%
LMArena Math14731407
FrontierMath (Feb 2025 set)35.6%32.4%
FrontierMath Tier 4 (v1)4.2%12.5%
MathArena Final-Answer Competitions67.6%—
Omni-MATH—64.7%
MATH Level 5—98.1%

Knowledge Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 58.8 (#33), GPT-5: 56.6 (#43)

BenchmarkGemini 3 Flash PreviewGPT-5
GPQA Diamond89.4%86.2%
SimpleQA Verified66.8%50.1%
Vectara Hallucination Rate13.5%14.7%
LMArena Expert14621419
Humanity's Last Exam—25.3%
MMLU-Pro—86.3%
Confabulations—10.3%
GPQA (HELM)—79.2%

Multimodal GPT-5 leads

Gemini 3 Flash Preview: 45.5 (#16), GPT-5: 46.8 (#13)

BenchmarkGemini 3 Flash PreviewGPT-5
LMArena Vision12851232
GeoBench88%81%
VPCT72.6%66%
Blueprint-Bench 20%—
LMArena Document1413—

Multilingual Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 55.7 (#27), GPT-5: 51.4 (#110)

BenchmarkGemini 3 Flash PreviewGPT-5
LMArena Non-English14581397
LMArena Chinese15111422
LMArena French14771410
LMArena German14971416
LMArena Japanese14891409
LMArena Korean14431360
LMArena Russian14801406
LMArena Spanish14691399

Instruction Following Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 75.7 (#56), GPT-5: 73.8 (#113)

BenchmarkGemini 3 Flash PreviewGPT-5
LMArena Instruction Following14371388
IFEval—87.5%

Long Context GPT-5 leads

Gemini 3 Flash Preview: 44.4 (#67), GPT-5: 69.5 (#2)

BenchmarkGemini 3 Flash PreviewGPT-5
LMArena Longer Query14521399
Fiction.LiveBench—97.2%

Writing & Preference Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 65.5 (#45), GPT-5: 63.4 (#65)

BenchmarkGemini 3 Flash PreviewGPT-5
LMArena Text14661406
LMArena Creative Writing14571365
LMArena Multi-Turn14711426
Short-Story Creative Writing—86%
EQ-Bench Creative Writing—1627
WildBench—85.7%

Frequently asked questions

Is Gemini 3 Flash Preview better than GPT-5?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 50.9 on the Noometry Index.

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

Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; GPT-5 lists at $1.25 and $10.

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

They score almost the same on coding (50.9 vs 50.3); test both on your own repository before choosing.

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 share?

48 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and GPT-5 has 69.

Related comparisons

Go deeper