🆕 NewMay 19, 2026
Gemini 3.5 Flash released
Google's speed tier announced at I/O 2026 punches above its weight: it beats Gemini 3.1 Pro on some coding benchmarks at about 25% lower cost.
Gemini 3.5 Flash
🧠 Reasoning🌐 Web Search
Google's speed tier that punches above its weight. Beats 3.1 Pro on coding at about 25% lower cost.
Released May 19, 2026
Pricing
Input tokens$1.50/M
Output tokens$9.00/M
Capacity
Context window1.0M tokens
Max output64K tokens
Capabilities
✓Reasoning & Planning
✓Web Search
✗Open Source
Best Scores
GDPval-AA v21348.8 pts
GPQA Diamond92.2%
SWE-bench Verified78.0%
Terminal-Bench 2.176.2%
SWE-bench Pro55.1%
Best For
💻coding
📊analysis
✍️writing
Benchmark Scores
Specialized Skills
GDPval-AA v2
Real paid work from 44 different jobs, such as law, nursing, and software. Judges compare two answers side by side without knowing which model wrote them, and the winner gains rating points. A typical human expert scores 1000, so a higher number means the work was picked over a human more often.
Provider-reported; no independent run recorded yet.
Knowledge
GPQA Diamond
PhD-level science questions written so you cannot just Google the answer. Tests whether the model can reason about hard science.
Independently measured by Artificial Analysis.
Humanity's Last Exam
PhD-level questions across many subjects. Tests deep reasoning on the hardest questions humans can ask.
Provider-reported; no independent run recorded yet.
Software Engineering
SWE-bench Verified
Hands the AI bugs from actual software projects and counts how many it fixes. Like a coding job interview, but with real work.
Provider-reported; no independent run recorded yet.
Terminal-Bench 2.1
Puts the AI in front of a computer terminal and asks it to finish multi-step tasks on its own. Measures how good an "AI agent" it is.
Provider-reported; an independent run by Vals AI (Terminus 2) lands at 74.16%.
SWE-bench Pro
The harder version of the coding test. Bigger codebases, trickier bugs. Scores drop for everyone, so the gaps between models become clearer.
Provider-reported; no independent run recorded yet.
Why Choose Gemini 3.5 Flash?
Flash is the rare speed-tier model that doesn't sacrifice much. It beats even Gemini 3.1 Pro on some coding benchmarks while being 25% cheaper. Best for teams who want Google's capabilities at a mid-tier price.
How It Compares
vs Gemini 3.1 Pro
Flash is cheaper and often outperforms Pro on coding; Pro is more consistent.
vs Claude Sonnet 5
Flash is more aligned with Google services; Sonnet is cheaper at intro pricing.