Noometry

Model comparison

Gemini 3.6 Flash vs GPT-4.5

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 37.2 on the Noometry Index.

Last verified . 24 shared benchmarks.

Gemini 3.6 Flash Google

54.1

Rank #33 Confirmed

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 10 categories and GPT-4.5 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.8 to 13.9.
  • The biggest single-benchmark swing is ARC-AGI-1: 91.2% for Gemini 3.6 Flash and 10.3% for GPT-4.5.

Side by side

Gemini 3.6 FlashGPT-4.5
ProviderGoogleOpenAI
Noometry Index54.137.2
Released2026-07-212025-02-27
WeightsProprietaryProprietary
Context window1.05M—
Max output66K—
Input $ / M tokens$0.75—
Output $ / M tokens$3.75—
Results tracked4642

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

Category by category

Coding Gemini 3.6 Flash leads

Gemini 3.6 Flash: 50.0 (#48), GPT-4.5: 42.2 (#109)

BenchmarkGemini 3.6 FlashGPT-4.5
WeirdML56.1%39.4%
LMArena Coding14911396
DeepSWE46.7%—
FrontierCode34.4%—
Aider Polyglot—44.9%
LMArena WebDev1538—
SciCode52.7%—
LiveBench Coding—75.2%
ALE-Bench715.52—

Agentic & Tool Use Gemini 3.6 Flash leads

Gemini 3.6 Flash: 32.3 (#65), GPT-4.5: 27.9 (#97)

BenchmarkGemini 3.6 FlashGPT-4.5
APEX-Agents46.9%—
Cybench—17.5%
GDP.pdf14%—

Reasoning Gemini 3.6 Flash leads

Gemini 3.6 Flash: 58.8 (#22), GPT-4.5: 13.9 (#330)

BenchmarkGemini 3.6 FlashGPT-4.5
ARC-AGI-260.4%0.8%
ARC-AGI-191.2%10.3%
LMArena Hard Prompts14851403
Epoch Capabilities Index154.25136.74
SimpleBench—34.5%
NYT Connections (extended)89%—
CritPt10.6%—
Chess Puzzles43%—
EnigmaEval—3.2%
LiveBench Reasoning—71.1%
Mystery Game Puzzles30%—
DTBench95.5%—
LiveBench Data Analysis—64.3%
LMCA44.9%—
ForecastBench—61.7
LiveBench—69%

Math Gemini 3.6 Flash leads

Gemini 3.6 Flash: 57.3 (#40), GPT-4.5: 32.6 (#211)

BenchmarkGemini 3.6 FlashGPT-4.5
OTIS Mock AIME 2024-202594.2%37.8%
LMArena Math15051412
FrontierMath (Tiers 1-3)58.9%—
FrontierMath Tier 422%—
MathArena Final-Answer Competitions70.8%—
ProofBench36%—
LiveBench Math—69.3%
MATH Level 5—78.6%

Knowledge Gemini 3.6 Flash leads

Gemini 3.6 Flash: 67.8 (#8), GPT-4.5: 32.5 (#211)

BenchmarkGemini 3.6 FlashGPT-4.5
GPQA Diamond94.1%68.7%
LMArena Expert14881394
Humanity's Last Exam—5.4%
SimpleQA Verified66.2%—
Confabulations—13.6%

Multimodal Too close to call

Gemini 3.6 Flash: 38.5 (#64), GPT-4.5: 37.6 (#71)

BenchmarkGemini 3.6 FlashGPT-4.5
LMArena Vision12981195
VPCT—45%
Blueprint-Bench 231.2%—
Furniture Assembly23.3%—
LMArena Document1456—

Multilingual Gemini 3.6 Flash leads

Gemini 3.6 Flash: 56.5 (#19), GPT-4.5: 52.5 (#83)

BenchmarkGemini 3.6 FlashGPT-4.5
LMArena Non-English14691413
LMArena Chinese15311421
LMArena French15041418
LMArena German14781457
LMArena Japanese14761416
LMArena Korean14311392
LMArena Russian14871419
LMArena Spanish1475—

Instruction Following Gemini 3.6 Flash leads

Gemini 3.6 Flash: 77.0 (#33), GPT-4.5: 72.6 (#134)

BenchmarkGemini 3.6 FlashGPT-4.5
LMArena Instruction Following14661404
LiveBench Instruction Following—72.3%

Long Context Gemini 3.6 Flash leads

Gemini 3.6 Flash: 45.1 (#50), GPT-4.5: 40.4 (#155)

BenchmarkGemini 3.6 FlashGPT-4.5
LMArena Longer Query14741406
Fiction.LiveBench—63.9%

Writing & Preference Gemini 3.6 Flash leads

Gemini 3.6 Flash: 68.2 (#27), GPT-4.5: 56.9 (#134)

BenchmarkGemini 3.6 FlashGPT-4.5
LMArena Text14791417
LMArena Creative Writing14651394
EQ-Bench Creative Writing16041258
LMArena Multi-Turn14811444
Short-Story Creative Writing—75.6%
LiveBench Language—61.5%

Frequently asked questions

Is Gemini 3.6 Flash better than GPT-4.5?

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 37.2 on the Noometry Index.

Is Gemini 3.6 Flash or GPT-4.5 better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 50.0 versus 42.2 in the Noometry coding category.

How many benchmarks do Gemini 3.6 Flash and GPT-4.5 share?

24 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and GPT-4.5 has 42.

Related comparisons

Go deeper