DataLearner logo

Gemini 3.7 FlashvsGemini 3.5 Flash

Across 5 shared benchmarks, Gemini 3.7 Flash leads overall: Gemini 3.7 Flash wins 5, Gemini 3.5 Flash wins 0, with 0 ties and an average score difference of +47.48.

Google Deep Mind
Gemini 3.7 Flash

Google Deep Mind · 2026-08-13 · Multimodal model

Google Deep Mind
Gemini 3.5 Flash

Google Deep Mind · 2026-06-20 · Multimodal model

Gemini 3.7 Flash5 wins(100%)(0%)0 winsGemini 3.5 Flash

Benchmark scores

Grouped by capability, sorted by largest gap within each. 5 shared benchmarks.

AI Agent - Tool Usage

Gemini 3.7 Flash 1/1
BenchmarkGemini 3.7 FlashGemini 3.5 FlashDiff
Terminal-Bench 2.185.809 / 44Thinking (With Tools)76.2023 / 44Thinking High (With Tools)+9.60

Coding and Software Engineer

Gemini 3.7 Flash 1/1
BenchmarkGemini 3.7 FlashGemini 3.5 FlashDiff
DeepSWE65.3010 / 27Thinking High (With Tools)3723 / 27Thinking Medium (With Tools)+28.30

Long Context

Gemini 3.7 Flash 1/1
BenchmarkGemini 3.7 FlashGemini 3.5 FlashDiff
GDM-MRCR v2 (8-needle, 128K)971 / 8Thinking Medium (No Tools)77.304 / 8Thinking (No Tools)+19.70

Multimodal Understanding

Gemini 3.7 Flash 1/1
BenchmarkGemini 3.7 FlashGemini 3.5 FlashDiff
CharXiv RQ88.704 / 15Thinking Medium (With Tools)84.908 / 15Thinking (With Tools)+3.80

Productivity Knowledge

Gemini 3.7 Flash 1/1
BenchmarkGemini 3.7 FlashGemini 3.5 FlashDiff
GDPval-AA v21,5258 / 13Thinking (No Tools)1,34911 / 13Thinking (No Tools)+176

Specs

FieldGemini 3.7 FlashGemini 3.5 Flash
PublisherGoogle Deep MindGoogle Deep Mind
Release date2026-08-132026-06-20
Model typeMultimodal modelMultimodal model
ArchitectureDenseDense
ParametersNot availableNot available
Context length1M1M
Max output64K64K

API pricing

Prices use DataLearner records when available; missing fields are not inferred.

ItemGemini 3.7 FlashGemini 3.5 Flash
Text input$0.75 / 1M tokens$1.5 / 1M tokens
Text output$3.75 / 1M tokens$9 / 1M tokens
Cache read$0.075 / 1M tokens$0.15 / 1M tokens

Summary

  • Gemini 3.7 Flashleads in:AI Agent - Tool Usage (1/1), Coding and Software Engineer (1/1), Long Context (1/1), Multimodal Understanding (1/1), Productivity Knowledge (1/1)

On average across the 5 shared benchmarks, Gemini 3.7 Flash scores 47.48 higher.

Largest single-benchmark gap: GDPval-AA v2 — Gemini 3.7 Flash 1,525 vs Gemini 3.5 Flash 1,349 (+176).

Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.