Noometry

Model comparison

Gemini 3.6 Flash vs GPT-5.2 Pro

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 52.3 on the Noometry Index.

Last verified . 6 shared benchmarks.

Gemini 3.6 Flash Google

54.1

Rank #33 Confirmed

GPT-5.2 Pro OpenAI

52.3

Rank #39 Reported

Summary

  • They share 6 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 1 category and GPT-5.2 Pro in 1 category; 2 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.2 Pro leads 65.3 to 57.3.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 22% for Gemini 3.6 Flash and 46% for GPT-5.2 Pro.
  • Gemini 3.6 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.
  • Gemini 3.6 Flash accepts more context: 1.05M tokens versus 400K.

Side by side

Gemini 3.6 FlashGPT-5.2 Pro
ProviderGoogleOpenAI
Noometry Index54.152.3
Released2026-07-212025-12-11
WeightsProprietaryProprietary
Context window1.05M400K
Max output66K128K
Input $ / M tokens$0.75$21
Output $ / M tokens$3.75$168
Results tracked468

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

Category by category

Coding Not comparable

Gemini 3.6 Flash: 50.0 (#48), GPT-5.2 Pro: —

BenchmarkGemini 3.6 FlashGPT-5.2 Pro
DeepSWE46.7%—
FrontierCode34.4%—
LMArena WebDev1538—
SciCode52.7%—
WeirdML56.1%—
LMArena Coding1491—
ALE-Bench715.52—

Agentic & Tool Use Not comparable

Gemini 3.6 Flash: 32.3 (#65), GPT-5.2 Pro: —

BenchmarkGemini 3.6 FlashGPT-5.2 Pro
APEX-Agents46.9%—
GDP.pdf14%—

Reasoning Gemini 3.6 Flash leads

Gemini 3.6 Flash: 58.8 (#22), GPT-5.2 Pro: 51.5 (#33)

BenchmarkGemini 3.6 FlashGPT-5.2 Pro
ARC-AGI-260.4%54.2%
NYT Connections (extended)89%79.3%
ARC-AGI-191.2%90.5%
Epoch Capabilities Index154.25155.4
SimpleBench—57.4%
CritPt10.6%—
Chess Puzzles43%—
LMArena Hard Prompts1485—
Mystery Game Puzzles30%—
DTBench95.5%—
LMCA44.9%—

Math GPT-5.2 Pro leads

Gemini 3.6 Flash: 57.3 (#40), GPT-5.2 Pro: 65.3 (#29)

BenchmarkGemini 3.6 FlashGPT-5.2 Pro
FrontierMath (Tiers 1-3)58.9%74%
FrontierMath Tier 422%46%
MathArena Final-Answer Competitions70.8%—
OTIS Mock AIME 2024-202594.2%—
ProofBench36%—
LMArena Math1505—
FrontierMath Tier 4 (v1)—31.3%

Knowledge Not comparable

Gemini 3.6 Flash: 67.8 (#8), GPT-5.2 Pro: —

BenchmarkGemini 3.6 FlashGPT-5.2 Pro
GPQA Diamond94.1%—
SimpleQA Verified66.2%—
LMArena Expert1488—

Multimodal Not comparable

Gemini 3.6 Flash: 38.5 (#64), GPT-5.2 Pro: —

BenchmarkGemini 3.6 FlashGPT-5.2 Pro
LMArena Vision1298—
Blueprint-Bench 231.2%—
Furniture Assembly23.3%—
LMArena Document1456—

Multilingual Not comparable

Gemini 3.6 Flash: 56.5 (#19), GPT-5.2 Pro: —

BenchmarkGemini 3.6 FlashGPT-5.2 Pro
LMArena Non-English1469—
LMArena Chinese1531—
LMArena French1504—
LMArena German1478—
LMArena Japanese1476—
LMArena Korean1431—
LMArena Russian1487—
LMArena Spanish1475—

Instruction Following Not comparable

Gemini 3.6 Flash: 77.0 (#33), GPT-5.2 Pro: —

BenchmarkGemini 3.6 FlashGPT-5.2 Pro
LMArena Instruction Following1466—

Long Context Not comparable

Gemini 3.6 Flash: 45.1 (#50), GPT-5.2 Pro: —

BenchmarkGemini 3.6 FlashGPT-5.2 Pro
LMArena Longer Query1474—

Writing & Preference Not comparable

Gemini 3.6 Flash: 68.2 (#27), GPT-5.2 Pro: —

BenchmarkGemini 3.6 FlashGPT-5.2 Pro
LMArena Text1479—
LMArena Creative Writing1465—
EQ-Bench Creative Writing1604—
LMArena Multi-Turn1481—

Frequently asked questions

Is Gemini 3.6 Flash better than GPT-5.2 Pro?

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 52.3 on the Noometry Index.

Which is cheaper, Gemini 3.6 Flash or GPT-5.2 Pro?

Gemini 3.6 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; GPT-5.2 Pro lists at $21 and $168.

Which has the bigger context window?

Gemini 3.6 Flash does, with 1.05M tokens against 400K.

How many benchmarks do Gemini 3.6 Flash and GPT-5.2 Pro share?

6 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and GPT-5.2 Pro has 8.

Related comparisons

Go deeper