LIVE
OPUS 4.7$15 / $75per Mtok
SONNET 4.6$3 / $15per Mtok
GPT-5.5$10 / $30per Mtok
GEMINI 3.1$3.50 / $10.50per Mtok
SWE-BENCHleader Claude Opus 4.772.1%
MMLU-PROleader Opus 4.788.4
VALS FINANCEleader Opus 4.764.4%
AFTAv1.0 whitepaper live at /whitepaper
OPUS 4.7$15 / $75per Mtok
SONNET 4.6$3 / $15per Mtok
GPT-5.5$10 / $30per Mtok
GEMINI 3.1$3.50 / $10.50per Mtok
SWE-BENCHleader Claude Opus 4.772.1%
MMLU-PROleader Opus 4.788.4
VALS FINANCEleader Opus 4.764.4%
AFTAv1.0 whitepaper live at /whitepaper
All systems operational0 AI providers monitored, polled every 2 minutes
Live status

Gemini 3.5 Flash vs Claude Sonnet 4.6

Gemini 3.5 Flash (May 19, 2026) and Claude Sonnet 4.6 occupy the same mid-tier slot but solve different sides of the daily-driver problem. Flash 3.5 is the first Flash-tier release to beat the previous Pro flagship on agentic coding suites (Terminal-Bench 2.1 at 76.2%, MCP Atlas at 83.6%) while running at roughly 289 output tokens per second and shipping a 1M-token input window. Sonnet 4.6 still leads on academic reasoning (MMLU-Pro 88.7) and code generation (HumanEval 92.0) at a 200K context, and remains the default for MCP-native agent stacks. The decision usually comes down to throughput and context vs raw English benchmark scores.

Head-to-Head Specs

SpecGemini 3.5 FlashClaude Sonnet 4.6
ProviderGoogleAnthropic
Input Price$1.50/1M$3.00/1M
Output Price$9.00/1M$15.00/1M
Context Window1.0M200K
Released2026-052026-03
Capabilitiestext, vision, tool-use, code, reasoningtext, vision, tool-use, code

Category Breakdown

Agentic coding (Terminal-Bench, MCP Atlas)Gemini 3.5 Flash

Flash 3.5 beats the previous Pro flagship on both suites at Flash-tier pricing.

Context windowGemini 3.5 Flash

Flash 3.5 has a 1,048,576 token input window vs Sonnet 4.6 at 200K. Roughly 5x more.

ThroughputGemini 3.5 Flash

Flash 3.5 runs at around 289 output tokens per second, roughly 4x the prior Gemini frontier tier.

Input pricingGemini 3.5 Flash

Flash 3.5 at $1.50/1M vs Sonnet 4.6 at $3/1M. Half the input cost.

Output pricingGemini 3.5 Flash

Flash 3.5 at $9/1M vs Sonnet 4.6 at $15/1M. Roughly 40 percent cheaper on output.

Code generation (HumanEval)Claude Sonnet 4.6

Sonnet 4.6 published HumanEval at 92.0; Google did not publish a HumanEval score for Flash 3.5.

General reasoning (MMLU-Pro)Claude Sonnet 4.6

Sonnet 4.6 at 88.7 published; Flash 3.5 MMLU-Pro is reported around 88.3 on third-party leaderboards.

MCP and tool useTieTie

Both are first-class MCP citizens. Anthropic owns the spec; Google scored 83.6 on the MCP Atlas suite.

Choose Gemini 3.5 Flash when:

  • Agentic coding and tool-use workflows at high throughput
  • RAG and long-document workloads (1M context)
  • Cost-sensitive mid-tier production at $1.50/$9 pricing
  • Workloads on Google Cloud / Vertex AI
View Gemini 3.5 Flash details

Choose Claude Sonnet 4.6 when:

  • English-heavy academic reasoning workloads
  • Anthropic ecosystem (Claude Code, MCP-first agent stacks)
  • Code generation where HumanEval and SWE-bench scores still drive selection
  • Teams standardized on the Claude API for safety and tool-use semantics
View Claude Sonnet 4.6 details

Frequently Asked Questions

Which is better, Gemini 3.5 Flash or Claude Sonnet 4.6?

It depends on your use case. Gemini 3.5 Flash from Google excels at agentic coding and tool-use workflows at high throughput, while Claude Sonnet 4.6 from Anthropic is better for english-heavy academic reasoning workloads. See the full comparison above for detailed benchmarks and pricing.

How much does Gemini 3.5 Flash cost compared to Claude Sonnet 4.6?

Gemini 3.5 Flash costs $1.50 input and $9.00 output per 1M tokens. Claude Sonnet 4.6 costs $3.00 input and $15.00 output per 1M tokens.

What is the context window difference between Gemini 3.5 Flash and Claude Sonnet 4.6?

Gemini 3.5 Flash supports 1.0M tokens, while Claude Sonnet 4.6 supports 200K tokens.

More Comparisons

Interactive Compare ToolAll ModelsFull Pricing Guide