Claude Sonnet 5 vs Gemini 3.7 Flash benchmark comparison

Verdict

Gemini 3.7 Flash leads overall

Ahead on 2 of 2 benchmarks, averaging 8.3 points higher

2
Comparable benchmarks: 2
Wins: 0
Losses: 0
Ties

Summarised from the 2 benchmarks both models were scored on; details in the charts below. A further 1 Elo/rating-scale benchmarks are left out of the average — their scale cannot be added to percentages.

Claude Sonnet 5

Anthropic

Release: 2026-06-30
Context length: 1M
Total parameters: Not provided
Max output length: 128,000 tokens
Runtime modes: 关闭 · 深度

Model profile

Metrics for the current filters

Updates live with the mode filters below.

Best overall

Claude Sonnet 5 · 640.67

Best single

Claude Sonnet 5 · Creative Writing 1787.60

Modality coverage

Gemini 3.7 Flash · 4 modalities

Head to head

Claude Sonnet 5

Gemini 3.7 Flash

AheadTiedBehind

Benchmarks

Wins

Losses

+15.07

Average diff

Performance benchmarks

Benchmark-by-benchmark comparison. Changing the thinking mode or tool filters updates the chart and table below.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Filter: Best Available·2 modes · 3 Benchmark

Loading chart…

Benchmark score table

Every model and runtime mode, benchmark by benchmark. Values are comparable along a row, not between different benchmarks.

3 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.

Benchmark	Claude Sonnet 5	Gemini 3.7 Flash
DeepSWE 编程与软件工程	54.00Deep Thinking Mode ｜ Tools	65.30Thinking Level · High ｜ Tools
Creative Writing 写作和创作	1787.60Standard Mode	1725.70Standard Mode
Terminal-Bench 2.1 AI Agent - 工具使用	80.40Thinking Level · Extra High ｜ Tools	85.80Thinking Enabled ｜ Tools

API price comparison

Official list prices per model API, split by input and output. Unit: USD per 1M tokens.

Specs & licensing

Architecture, licensing and API modalities. "Not provided" means the field is missing from our database.

Features & specs	Claude Sonnet 5Anthropic	Gemini 3.7 FlashGoogle Deep Mind
Core specsRelease	2026-06-30	2026-08-13
Context length	1M	1M
Max output length	128,000 tokens	65,536 tokens
Architecture	Dense	Dense
Runtime modes	关闭深度	中低高
LicenseCode Open Source	Closed Source	Closed Source
Weights Open Source	Closed Source	Closed Source
Licensing status	不开源	不开源
API modality supportText Input/Output	/	/
Image Input/Output	/	/
Audio Input/Output	Not provided	/
Video Input/Output	Not provided	/
ResourcesPaper / report	Introducing Claude Sonnet 5	Gemini 3.7 Flash