Gemini 3.5 Flash
Released
Gemini 3.5 Flash is an AI model released by Google on Tuesday, May 19 2026, 47 days after Gemma 4. Benchmark results (shown below) cover Toolathlon, MMMU-Pro, BullshitBench v2, Gray Swan IPI, ProgramBench, SWE-Bench Pro, and 14 more.
Get Google releases and AI news.
Every other Monday
API pricing
- InputWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it.
- $1.50
- Cached inputA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again.
- $0.15
- OutputWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one.
- $9.00
Available from
| global | flex | $0.75 | $4.50 | 1M | |
| Google AI Studio | — | flex | $0.75 | $4.50 | 1M |
| global | — | $1.50 | $9.00 | 1M | |
| Google AI Studio | — | — | $1.50 | $9.00 | 1M |
| us | — | $1.65 | $9.90 | 1M | |
| global | priority | $2.70 | $16.20 | 1M | |
| Google AI Studio | — | priority | $2.70 | $16.20 | 1M |
Benchmarks
Coding
ProgramBenchProgram reconstruction — The AI receives a working program and its documentation, then builds a replacement from scratch without the original source code, internet access or decompilation. The score is the percentage of 200 programs that pass every behavioral test. We record each model's best published mini-SWE-agent result, including higher reasoning efforts where available. Partial test-pass rates and almost-solved programs do not count toward this score. Equal scores share a rank here; the official board also uses partial progress to break ties. Higher is better.via ProgramBench
0%
#5 of 17Best: Claude Opus 5 · 4.5%
SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better.
55.1%
#15 of 23Best: Claude Fable 5.1 · 81.2%
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better.
37%
#27 of 31Best: Gemini 4 Argon · 77.9%
MLE-BenchML engineering — Can the AI do the work of a machine-learning engineer? It competes in real Kaggle competitions — building, training, and tuning models end to end — and the score reflects how well it places. Higher is better.
49.7%
#2 of 3Best: Gemini 3.6 Flash · 63.9%
Terminal & CLI
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better.
76.2%
#22 of 32Best: DeepSeek-V4.1-Flash · 90.6%
Agentic & tool use
ToolathlonGeneral tool use — Tests how well the AI uses everyday real-world tools and apps to get things done. Higher is better.
56.5%
#1Best published Toolathlon score of all tracked models
MCP AtlasMulti-step tool use — Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better.
83.6%
#3 of 11Best: Muse Spark 1.1 · 88.1%
BU BenchBrowser agent — Can the AI drive a real web browser to finish tasks — clicking, filling forms, and navigating sites the way a person would? Run by Browser Use on their BU Bench task set. Higher is better.
58%
#5 of 7Best: Claude Opus 4.8 · 74%
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better.
78.4%
#10 of 28Best: Qwen3.8-Max · 86.1%
Reasoning & science
Humanity's Last ExamMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better.via BenchLM
40.2%no tools
40.2%with tools
no tools
#11 of 22Best: Claude Fable 5.1 · 60.9%
with tools
#31 of 45Best: Claude Opus 5.5 · 67.7%
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better.
72.1%
#16 of 34Best: GPT-6 Astra · 95%
Knowledge work
GDPval-AAKnowledge work — Measures how well the AI does economically valuable knowledge work, judged against human experts. Shown as a rating (like a chess Elo) — higher is better.
1656
#6 of 9Best: Claude Fable 5 · 1932
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo)
1349
#17 of 20Best: Claude Opus 5 · 1861
Finance
Finance Agent v2Agentic financial analysis — Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better.
57.9%
#3 of 10Best: Gemini 4 Argon · 65.4%
Multimodal
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better.
83.6%
#1Best published MMMU-Pro score of all tracked models
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better.
84.2%
#8 of 16Best: Muse Spark · 88.9%
Blueprint-Bench 2Spatial reasoning — Can the AI reason about space and layout — for example, understanding a floor plan or blueprint? Higher is better.
33.6%
#2 of 6Best: GPT-5.5 · 36.2%
Long context
MRCR v2 (8-needle)Long context — Tests whether the AI can find specific details buried inside a very long document (around 128k tokens — roughly a long book). Higher is better.
77.3%128k average
26.6%1M pointwise
128k average
#5 of 7Best: Gemini 3.7 Flash · 97%
1M pointwise
#2 of 4Best: Gemini 3.7 Flash · 62.5%
Robustness
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better.
20%
#62 of 84Best: Claude Opus 4.8 · 95%
Gray Swan IPIPrompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. Gray Swan's indirect prompt injection benchmark measures how often such an attack succeeds when the attacker gets a single try. Lower is better.
14.1%k = 1
54.2%k = 10
60.5%k = 15
k = 1
#12 of 13Best: Claude Opus 5 · 0.2%
k = 10
#12 of 13Best: Claude Opus 5 · 1.6%
k = 15
#13 of 14Best: Gemini 4 Argon · 0.7%
Source: ProgramBench, retrieved 11 September 2026 · Source: BenchLM, retrieved 31 August 2026. Other sources are identified on the linked benchmark pages.
Compare Gemini 3.5 Flash with
Suggested comparisons
Gemini 3.5 FlashvsGemini 4 ArgonGemini 3.5 FlashvsGPT-6.1 SolGemini 3.5 FlashvsClaude Sonnet 5.5Gemini 3.5 FlashvsMuse Spark 1.3Gemini 3.5 FlashvsGrok 4.7Gemini 3.5 FlashvsDeepSeek-V4.1-FlashGemini 3.5 FlashvsMistral Medium 3.5Gemini 3.5 FlashvsKimi K3Gemini 3.5 FlashvsGLM-5.3-FlashGemini 3.5 FlashvsQwen3.8-Max-0902Gemini 3.5 FlashvsNemotron 3.5 LightningFrequently asked questions
Gemini 3.5 Flash was released by Google on Tuesday, May 19 2026.
All Google releases
31 tracked2026
11 releasesGemini 4 Argon
Sep 30 2026
Gemini 3.8 Flash
Sep 2 2026
Gemini 3.8 Flash Cyber
Sep 2 2026
Gemini 3.7 Flash
Aug 13 2026
Gemini 3.6 Flash
Jul 21 2026
Gemini 3.5 Flash-Lite
Jul 21 2026
Gemini 3.5 Flash Cyber
Jul 21 2026
Gemini 3.5 Flash
May 19 2026
Gemma 4
Apr 2 2026
Gemini 3.1 Flash-Lite
Mar 3 2026
Gemini 3.1 Pro
Feb 19 2026