Noometry

Model comparison

Gemini 3.7 Flash vs GPT-4

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 29.1 on the Noometry Index.

Last verified . 25 shared benchmarks.

Gemini 3.7 Flash Google

59.8

Rank #14 Confirmed

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Gemini 3.7 Flash scores higher in 8 categories and GPT-4 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemini 3.7 Flash leads 69.6 to 10.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 97.2% for Gemini 3.7 Flash and 1.1% for GPT-4.
  • Gemini 3.7 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $30 / $60 for GPT-4.
  • Gemini 3.7 Flash accepts more context: 1.05M tokens versus 8K.

Side by side

Gemini 3.7 FlashGPT-4
ProviderGoogleOpenAI
Noometry Index59.829.1
Released2026-08-132023-03-14
WeightsProprietaryProprietary
Context window1.05M8K
Max output66K8K
Input $ / M tokens$0.75$30
Output $ / M tokens$3.75$60
Results tracked4438

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

Category by category

Coding Gemini 3.7 Flash leads

Gemini 3.7 Flash: 56.2 (#22), GPT-4: 31.6 (#283)

BenchmarkGemini 3.7 FlashGPT-4
LMArena Coding14971254
DeepSWE65.5%—
FrontierCode43.6%—
LMArena WebDev1592—
FrontierSWE20.3%—
SciCode59.8%—
WeirdML—12.4%
BigCodeBench Instruct—46%
BigCodeBench Complete—57.2%
ALE-Bench904.3—
HumanEval+—79.3%

Agentic & Tool Use Not comparable

Gemini 3.7 Flash: 42.1 (#19), GPT-4: —

BenchmarkGemini 3.7 FlashGPT-4
APEX-Agents67.8%—
Remote Labor Index5%—
GDP.pdf23.8%—
METR Time Horizons—36.1%

Reasoning Gemini 3.7 Flash leads

Gemini 3.7 Flash: 70.0 (#15), GPT-4: 17.8 (#289)

BenchmarkGemini 3.7 FlashGPT-4
Chess Puzzles47%4%
LMArena Hard Prompts14941241
Mystery Game Puzzles37%12%
DTBench96.8%62.7%
LMCA50.4%17.1%
Epoch Capabilities Index157.27125.89
ARC-AGI-284.6%—
NYT Connections (extended)94%—
ARC-AGI-195.5%—
CritPt14.3%—
BIG-Bench Hard—75.1%
ForecastBench—57.8
HellaSwag—95.3%
WinoGrande—87.5%

Math Gemini 3.7 Flash leads

Gemini 3.7 Flash: 69.6 (#23), GPT-4: 10.8 (#309)

BenchmarkGemini 3.7 FlashGPT-4
OTIS Mock AIME 2024-202597.2%1.1%
LMArena Math15071269
FrontierMath (Tiers 1-3)71.6%—
FrontierMath Tier 436.6%—
ProofBench58%—
MATH Level 5—23%
GSM8K—92%

Knowledge Gemini 3.7 Flash leads

Gemini 3.7 Flash: 69.7 (#5), GPT-4: 18.4 (#282)

BenchmarkGemini 3.7 FlashGPT-4
GPQA Diamond94.8%35.7%
LMArena Expert15081211
SimpleQA Verified69.2%—
MMLU—86.4%
TriviaQA—84.8%

Multimodal Not comparable

Gemini 3.7 Flash: 37.3 (#73), GPT-4: —

BenchmarkGemini 3.7 FlashGPT-4
LMArena Vision1316—
Furniture Assembly26.7%—

Multilingual Gemini 3.7 Flash leads

Gemini 3.7 Flash: 57.6 (#7), GPT-4: 40.6 (#215)

BenchmarkGemini 3.7 FlashGPT-4
LMArena Non-English14841246
LMArena Chinese15481242
LMArena French15051283
LMArena German14981251
LMArena Japanese15121209
LMArena Korean14831184
LMArena Russian15161251
LMArena Spanish15031261

Instruction Following Gemini 3.7 Flash leads

Gemini 3.7 Flash: 77.7 (#15), GPT-4: 65.3 (#222)

BenchmarkGemini 3.7 FlashGPT-4
LMArena Instruction Following14831241

Long Context Gemini 3.7 Flash leads

Gemini 3.7 Flash: 45.7 (#30), GPT-4: 37.7 (#212)

BenchmarkGemini 3.7 FlashGPT-4
LMArena Longer Query14921244

Writing & Preference Gemini 3.7 Flash leads

Gemini 3.7 Flash: 71.2 (#20), GPT-4: 34.9 (#268)

BenchmarkGemini 3.7 FlashGPT-4
LMArena Text14861263
LMArena Creative Writing14901244
EQ-Bench Creative Writing1723752
LMArena Multi-Turn14891257

Frequently asked questions

Is Gemini 3.7 Flash better than GPT-4?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 29.1 on the Noometry Index.

Which is cheaper, Gemini 3.7 Flash or GPT-4?

Gemini 3.7 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; GPT-4 lists at $30 and $60.

Is Gemini 3.7 Flash or GPT-4 better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 56.2 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.7 Flash does, with 1.05M tokens against 8K.

How many benchmarks do Gemini 3.7 Flash and GPT-4 share?

25 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and GPT-4 has 38.

Related comparisons

Go deeper