DataLearner logo

Gemini 3.5 FlashvsClaude Sonnet 4.6

Across 7 shared benchmarks, Gemini 3.5 Flash leads overall: Gemini 3.5 Flash wins 5, Claude Sonnet 4.6 wins 2, with 0 ties and an average score difference of +4.92.

Google Deep Mind
Gemini 3.5 Flash

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

Anthropic
Claude Sonnet 4.6

Anthropic · 2026-02-17 · Chat model

Gemini 3.5 Flash5 wins(71%)(29%)2 winsClaude Sonnet 4.6

Benchmark scores

Grouped by capability, sorted by largest gap within each. 7 shared benchmarks.

General Knowledge

Claude Sonnet 4.6 2/3
BenchmarkGemini 3.5 FlashClaude Sonnet 4.6Diff
ARC-AGI-272.1013 / 62Thinking High (With Tools)58.3021 / 62+13.80
HLE40.2066 / 181Thinking High (With Tools)4934 / 181-8.80
LiveBench75.0217 / 115Thinking High (No Tools)75.4712 / 115Thinking Medium (No Tools)-0.45

AI Agent - Tool Usage

Gemini 3.5 Flash 2/2
BenchmarkGemini 3.5 FlashClaude Sonnet 4.6Diff
MCP-Atlas83.604 / 38Thinking High (With Tools)69.5027 / 38Normal (With Tools)+14.10
OSWorld-Verified78.4010 / 26Thinking High (With Tools)72.5017 / 26+5.90

Coding and Software Engineer

Gemini 3.5 Flash 1/1
BenchmarkGemini 3.5 FlashClaude Sonnet 4.6Diff
DeepSWE3722 / 26Thinking Medium (With Tools)3024 / 26Thinking High (With Tools)+7

General Evaluation

Gemini 3.5 Flash 1/1
BenchmarkGemini 3.5 FlashClaude Sonnet 4.6Diff
GPQA Diamond92.8019 / 226Thinking High (No Tools)89.9042 / 226+2.90

Specs

FieldGemini 3.5 FlashClaude Sonnet 4.6
PublisherGoogle Deep MindAnthropic
Release date2026-06-202026-02-17
Model typeMultimodal modelChat model
ArchitectureDenseDense
ParametersNot availableNot available
Context length1M1M
Max output64K8K

API pricing

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

ItemGemini 3.5 FlashClaude Sonnet 4.6
Text input$1.5 / 1M tokens$3 / 1M tokens
Text output$9 / 1M tokens$15 / 1M tokens
Cache read$0.15 / 1M tokens$0.3 / 1M tokens
Cache writeNot public$3.75 / 1M tokens

Summary

  • Gemini 3.5 Flashleads in:AI Agent - Tool Usage (2/2), Coding and Software Engineer (1/1), General Evaluation (1/1)
  • Claude Sonnet 4.6leads in:General Knowledge (2/3)

On average across the 7 shared benchmarks, Gemini 3.5 Flash scores 4.92 higher.

Largest single-benchmark gap: MCP-Atlas — Gemini 3.5 Flash 83.60 vs Claude Sonnet 4.6 69.50 (+14.10).

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