DataLearner logo

Gemini 3.5 FlashvsGemini 3.0 Flash

Across 8 shared benchmarks, Gemini 3.5 Flash leads overall: Gemini 3.5 Flash wins 7, Gemini 3.0 Flash wins 1, with 0 ties and an average score difference of +14.65.

Google Deep Mind
Gemini 3.5 Flash

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

Google Deep Mind
Gemini 3.0 Flash

Google Deep Mind · 2025-12-17 · Chat model

Gemini 3.5 Flash7 wins(88%)(13%)1 winGemini 3.0 Flash

Benchmark scores

Grouped by capability, sorted by largest gap within each. 8 shared benchmarks.

General Knowledge

Gemini 3.5 Flash 2/3
BenchmarkGemini 3.5 FlashGemini 3.0 FlashDiff
ARC-AGI-272.1013 / 62Thinking High (With Tools)33.6030 / 62+38.50
LiveBench75.0217 / 115Thinking High (No Tools)56.3579 / 115Normal (No Tools)+18.67
HLE40.2066 / 181Thinking High (With Tools)43.5050 / 181-3.30

AI Agent - Tool Usage

Gemini 3.5 Flash 2/2
BenchmarkGemini 3.5 FlashGemini 3.0 FlashDiff
MCP-Atlas83.604 / 38Thinking High (With Tools)6231 / 38Normal (With Tools)+21.60
Terminal-Bench 2.176.2022 / 43Thinking High (With Tools)5839 / 43Thinking High (With Tools)+18.20

Coding and Software Engineer

Gemini 3.5 Flash 1/1
BenchmarkGemini 3.5 FlashGemini 3.0 FlashDiff
SWE-Bench Pro - Public55.1030 / 57Thinking High (With Tools)49.6045 / 57Thinking High (With Tools)+5.50

Commonsense Reasoning

Gemini 3.5 Flash 1/1
BenchmarkGemini 3.5 FlashGemini 3.0 FlashDiff
SimpleBench76.704 / 67Normal (No Tools)61.1017 / 67Normal (No Tools)+15.60

General Evaluation

Gemini 3.5 Flash 1/1
BenchmarkGemini 3.5 FlashGemini 3.0 FlashDiff
GPQA Diamond92.8019 / 226Thinking High (No Tools)90.4036 / 226+2.40

Specs

FieldGemini 3.5 FlashGemini 3.0 Flash
PublisherGoogle Deep MindGoogle Deep Mind
Release date2026-06-202025-12-17
Model typeMultimodal modelChat model
ArchitectureDenseDense
ParametersNot availableNot available
Context length1M2000K
Max output64K64K

API pricing

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

ItemGemini 3.5 FlashGemini 3.0 Flash
Text input$1.5 / 1M tokens$0.5 / 1M tokens
Text output$9 / 1M tokens$3 / 1M tokens
Cache read$0.15 / 1M tokensNot public

Summary

  • Gemini 3.5 Flashleads in:General Knowledge (2/3), AI Agent - Tool Usage (2/2), Coding and Software Engineer (1/1), Commonsense Reasoning (1/1), General Evaluation (1/1)

On average across the 8 shared benchmarks, Gemini 3.5 Flash scores 14.65 higher.

Largest single-benchmark gap: ARC-AGI-2 — Gemini 3.5 Flash 72.10 vs Gemini 3.0 Flash 33.60 (+38.50).

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