Gemini 3.6 Flash
google/gemini-3.6-flash-20260721
Google's Gemini 3.6 Flash is a multimodal model that accepts text, image, video, file, and audio inputs and produces text output. It supports tool usage and reasoning and can handle contexts up to 1,048,576 tokens. Pricing is set at 1.5 per million input tokens and 7.5 per million output tokens.
- tool use
- structured outputs
- reasoning
At a glance
Specifications
What the API gives you
- Context window
- 1.0M tokens
- Max output
- 66K tokens
- Input price
- $0.75 / 1M tokens
- Output price
- $3.75 / 1M tokens
- Cache read
- $0.075 / 1M tokens
- Modalities
- text, image, video, file, audio → text
- Knowledge cutoff
- —
- Released
- Jul 9, 2026
Measured evidence
Public benchmark record
- Design Arena Coding
- 1290 Elo2026-10-20
- Design Arena Full-stack Agent
- 1181 Elo2026-10-14
- Design Arena UI
- 1297 Elo2026-10-20
- Design Arena Web-app Agent
- 1194 Elo2026-10-20
- Design Arena Website
- 1300 Elo2026-10-20
- FACTS Grounding
- 72.5%2026-07-22evaluated 2026-07-22
- FrontierMath Tiers 1-3 (Epoch AI)‡
- 58.9% ± 2.92026-08-02high effort, evaluated 2026-08-02
- GPQA Diamond (Epoch AI)‡
- 85.9% ± 2.52026-08-07minimal effort, evaluated 2026-08-07
- GPQA Diamond (Epoch AI)‡
- 86.4% ± 2.42026-08-06low effort, evaluated 2026-08-06
- GPQA Diamond (Epoch AI)‡
- 94.1% ± 1.42026-08-02high effort, evaluated 2026-08-02
- LiveBench Agentic Coding
- 43.4%2026-10-18
- LiveBench Coding
- 77.9%2026-10-18
- LiveBench Data Analysis
- 63%2026-10-18
- LiveBench Instruction Following
- 75.4%2026-10-18
- LiveBench Language
- 83.9%2026-10-18
- LiveBench Math
- 86.4%2026-10-18
- LiveBench Reasoning
- 85.2%2026-10-18
- LMArena Agent Bash Recovery‡
- -18.22026-10-08high effort
- LMArena Creative Writing
- 1466 Elo2026-10-15
- LMArena Instruction Following
- 1467 Elo2026-10-15
- LMArena Long Query
- 1474 Elo2026-10-15
- LMArena Math
- 1506 Elo2026-10-15
- LMArena Text
- 1483 Elo2026-10-15
- LMArena Text Factuality
- 1471 Elo2026-10-15
- LMArena Vision‡
- 1282 Elo2026-10-19high effort
- LMArena Vision Diagrams‡
- 1310 Elo2026-10-19high effort
- LMArena Vision OCR‡
- 1301 Elo2026-10-19high effort
- LMArena WebDev Image-to-Web‡
- 1545 Elo2026-10-19high effort
- OTIS Mock AIME (Epoch AI)‡
- 82.2% ± 5.82026-08-07low effort, evaluated 2026-08-07
- OTIS Mock AIME (Epoch AI)‡
- 94.2% ± 3.12026-08-02high effort, evaluated 2026-08-02
- SimpleQA Verified (Epoch AI)‡
- 66.2% ± 1.52026-08-27high effort, evaluated 2026-08-27
LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. ‡ Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.
Task evidence
How broad is the support?
Each status is exact to this model version and the selected task. Official release claims remain provisional.
- Best LLM for Competition MathEstablished evidence
100% of intended weighted task evidence across 4 independent sources. 6 of 6 configured evaluation feeds currently have results.
- Best LLM for Business WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for Logic & Problem SolvingEstablished evidence
100% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Marketing CopyEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for Chat & RoleplayEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for Creative WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.
Show all 41 tasks
- Best LLM for WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for Roleplay & CharacterEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for Math & ReasoningEstablished evidence
100% of intended weighted task evidence across 5 independent sources. 7 of 7 configured evaluation feeds currently have results.
- Best LLM for a General AssistantEstablished evidence
100% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.
- Best LLM for Document SummarizationEstablished evidence
85% of intended weighted task evidence across 3 independent sources. 5 of 6 configured evaluation feeds currently have results.
- Best LLM for SummarizationEstablished evidence
85% of intended weighted task evidence across 3 independent sources. 5 of 6 configured evaluation feeds currently have results.
- Best LLM for Frontend & UIEstablished evidence
73% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.
- Best Open-Weight LLM for Self-HostingEstablished evidence
64% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.
- Best LLM for Grounded RAGEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 7 configured evaluation feeds currently have results.
- Best LLM for Image UnderstandingEstablished evidence
61% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.
- Best LLM for RAG & Long ContextEstablished evidence
61% of intended weighted task evidence across 2 independent sources. 5 of 6 configured evaluation feeds currently have results.
- Best LLM for Fast SummariesEstablished evidence
58% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.
- Best Value LLMEstablished evidence
58% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.
- Best LLM for Literary TranslationEstablished evidence
50% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Everyday TranslationEstablished evidence
50% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for TranslationEstablished evidence
50% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Agentic CodingEstablished evidence
45% of intended weighted task evidence across 3 independent sources. 7 of 7 configured evaluation feeds currently have results.
- Best Cheap LLM for High VolumeEstablished evidence
40% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.
- Cheapest Capable LLMEstablished evidence
40% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.
- Best LLM for JSON & Schema OutputEstablished evidence
35% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Structured Data ExtractionEstablished evidence
35% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for CodingEstablished evidence
33% of intended weighted task evidence across 2 independent sources. 7 of 7 configured evaluation feeds currently have results.
- Best LLM for OCR & DocumentsProvisional evidence
65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Charts & DiagramsProvisional evidence
65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results. Official release evidence is also tracked provisionally.
- Best LLM for Vision & DocumentsProvisional evidence
60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 4 of 6 configured evaluation feeds currently have results. Official release evidence is also tracked provisionally.
- Best LLM for Document ParsingProvisional evidence
58% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Massive ContextProvisional evidence
47% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LongBench v2. 2 of 3 configured evaluation feeds currently have results.
- Best LLM for Code CompletionProvisional evidence
43% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LMArena WebDev. 3 of 3 configured evaluation feeds currently have results.
- Best Local LLM for CodingProvisional evidence
26% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LMArena WebDev. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for High-Volume ExtractionProvisional evidence
21% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Route reliability or Structured-output eval. 1 of 3 configured evaluation feeds currently have results.
- Best LLM for Debugging & Code ReviewProvisional evidence
17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LMArena WebDev. 5 of 5 configured evaluation feeds currently have results. Official release evidence is also tracked provisionally.
- Best LLM for Autonomous AgentsProvisional evidence
13% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or LMArena Agent Task Outcome. 6 of 6 configured evaluation feeds currently have results.
- Best LLM for AI AgentsProvisional evidence
9% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 9 of 9 configured evaluation feeds currently have results. Official release evidence is also tracked provisionally.
- Best LLM for Tool & Function CallingProvisional evidence
Official release evidence found; independent confirmation is still missing from Berkeley Function Calling or LMArena Agent.
- Best LLM for Computer & Browser UseProvisional evidence
Official release evidence found; independent confirmation is still missing from Berkeley Function Calling or LMArena Agent.
Official release evidence · provisional
What the launch material actually says
Verbatim claims from the model provider. These help on launch day but do not count as independent confirmation.
“3.6 Flash delivers higher precision with fewer unwanted code edits and reduced execution loops, as seen in DeepSWE (49% vs. 37%), and shows significant improvement in ML Research, as seen in MLE Bench (63.9% vs. 49.7%).”
Google · 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber“It has improved computer use capabilities as seen in OSWorld-Verified (83.0% vs. 78.4%). Computer use is now a built-in client side tool via the Gemini API and Gemini Enterprise.”
Google · 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber“It outperforms 3.5 Flash in knowledge work, as shown by benchmarks like GDPval-AA v2 (1421 vs. 1349).”
Google · 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber“Customers like Hebbia and Harvey have found it particularly capable at multimodal tasks like document parsing, chart and data analysis, and report drafting.”
Google · 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber
Recommendation coverage
Where this model appears
Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.