Gemini 3.7 Flash
google/gemini-3.7-flash-20260813
Google Gemini 3.7 Flash is a multimodal model that accepts text, image, video, file, and audio inputs and generates text outputs. It has a context length of 1,048,576 tokens, supports tool use and reasoning, and is a proprietary model released on August 13, 2026.
- 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
- Aug 13, 2026
Measured evidence
Public benchmark record
- Design Arena Coding
- 1331 Elo2026-08-18
- Design Arena Coding
- 1336 Elo2026-08-21
- Design Arena Coding
- 1333 Elo2026-08-19
- Design Arena Coding
- 1329 Elo2026-08-27
- Design Arena Coding
- 1333 Elo2026-08-20
- Design Arena Coding
- 1340 Elo2026-08-17
- Design Arena Coding
- 1334 Elo2026-08-22
- Design Arena Coding
- 1333 Elo2026-08-23
- Design Arena Coding
- 1328 Elo2026-08-28
- Design Arena Coding
- 1331 Elo2026-08-24
- Design Arena Coding
- 1331 Elo2026-08-25
- Design Arena Coding
- 1330 Elo2026-08-26
- Design Arena Coding
- 1328 Elo2026-08-29
- Design Arena Coding
- 1328 Elo2026-08-30
- Design Arena Coding
- 1328 Elo2026-08-31
- Design Arena Coding
- 1328 Elo2026-09-01
- Design Arena Coding
- 1326 Elo2026-09-02
- Design Arena Coding
- 1324 Elo2026-09-03
- Design Arena Coding
- 1323 Elo2026-09-04
- Design Arena Full-stack Agent
- 1233 Elo2026-08-27
- Design Arena Full-stack Agent
- 1228 Elo2026-08-28
- Design Arena Full-stack Agent
- 1229 Elo2026-08-29
- Design Arena Full-stack Agent
- 1224 Elo2026-08-30
- Design Arena Full-stack Agent
- 1223 Elo2026-08-31
- Design Arena Full-stack Agent
- 1220 Elo2026-09-01
- Design Arena Full-stack Agent
- 1221 Elo2026-09-02
- Design Arena Full-stack Agent
- 1222 Elo2026-09-03
- Design Arena Full-stack Agent
- 1221 Elo2026-09-04
- Design Arena UI
- 1312 Elo2026-08-18
- Design Arena UI
- 1308 Elo2026-08-19
- Design Arena UI
- 1306 Elo2026-08-27
- Design Arena UI
- 1308 Elo2026-08-20
- Design Arena UI
- 1322 Elo2026-08-17
- Design Arena UI
- 1322 Elo2026-08-21
- Design Arena UI
- 1317 Elo2026-08-22
- Design Arena UI
- 1318 Elo2026-08-23
- Design Arena UI
- 1309 Elo2026-08-28
- Design Arena UI
- 1320 Elo2026-08-24
- Design Arena UI
- 1310 Elo2026-08-25
- Design Arena UI
- 1307 Elo2026-08-26
- Design Arena UI
- 1310 Elo2026-08-29
- Design Arena UI
- 1309 Elo2026-08-30
- Design Arena UI
- 1313 Elo2026-08-31
- Design Arena UI
- 1309 Elo2026-09-01
- Design Arena UI
- 1311 Elo2026-09-02
- Design Arena UI
- 1306 Elo2026-09-03
- Design Arena UI
- 1304 Elo2026-09-04
- Design Arena Web-app Agent
- 1237 Elo2026-08-27
- Design Arena Web-app Agent
- 1244 Elo2026-08-28
- Design Arena Web-app Agent
- 1242 Elo2026-08-29
- Design Arena Web-app Agent
- 1244 Elo2026-08-30
- Design Arena Web-app Agent
- 1246 Elo2026-08-31
- Design Arena Web-app Agent
- 1246 Elo2026-09-01
- Design Arena Web-app Agent
- 1245 Elo2026-09-02
- Design Arena Web-app Agent
- 1245 Elo2026-09-03
- Design Arena Web-app Agent
- 1245 Elo2026-09-04
- Design Arena Website
- 1318 Elo2026-08-18
- Design Arena Website
- 1318 Elo2026-08-19
- Design Arena Website
- 1347 Elo2026-08-16
- Design Arena Website
- 1318 Elo2026-08-20
- Design Arena Website
- 1322 Elo2026-08-27
- Design Arena Website
- 1320 Elo2026-08-17
- Design Arena Website
- 1325 Elo2026-08-21
- Design Arena Website
- 1323 Elo2026-08-22
- Design Arena Website
- 1324 Elo2026-08-23
- Design Arena Website
- 1322 Elo2026-08-24
- Design Arena Website
- 1321 Elo2026-08-28
- Design Arena Website
- 1323 Elo2026-08-25
- Design Arena Website
- 1322 Elo2026-08-26
- Design Arena Website
- 1321 Elo2026-08-29
- Design Arena Website
- 1321 Elo2026-08-30
- Design Arena Website
- 1321 Elo2026-08-31
- Design Arena Website
- 1322 Elo2026-09-01
- Design Arena Website
- 1320 Elo2026-09-02
- Design Arena Website
- 1318 Elo2026-09-03
- Design Arena Website
- 1317 Elo2026-09-04
- Frontier-Bench‡
- 11.2%2026-08-13mini-SWE-agent, high effort
- LiveBench Agentic Coding
- 58.3%2026-06-25
- LiveBench Coding
- 78.9%2026-06-25
- LiveBench Data Analysis
- 68.0%2026-06-25
- LiveBench Instruction Following
- 79.9%2026-06-25
- LiveBench Language
- 85.5%2026-06-25
- LiveBench Math
- 93.5%2026-06-25
- LiveBench Reasoning
- 87.8%2026-06-25
- LMArena Agent
- 3.62026-08-13
- LMArena Agent
- 1.62026-08-24
- LMArena Agent
- 1.32026-08-27
- LMArena Agent
- 12026-08-31
- LMArena Creative Writing
- 1490 Elo2026-08-21
- LMArena Creative Writing
- 1490 Elo2026-08-27
- LMArena Creative Writing
- 1492 Elo2026-09-01
- LMArena Instruction Following
- 1486 Elo2026-08-21
- LMArena Instruction Following
- 1486 Elo2026-08-27
- LMArena Instruction Following
- 1485 Elo2026-09-01
- LMArena Long Query
- 1492 Elo2026-08-21
- LMArena Long Query
- 1492 Elo2026-08-27
- LMArena Long Query
- 1493 Elo2026-09-01
- LMArena Math
- 1527 Elo2026-08-21
- LMArena Math
- 1528 Elo2026-08-27
- LMArena Math
- 1527 Elo2026-09-01
- LMArena Text
- 1490 Elo2026-08-21
- LMArena Text
- 1490 Elo2026-08-27
- LMArena Text
- 1491 Elo2026-09-01
- LMArena WebDev
- 1587 Elo2026-08-14
- LMArena WebDev
- 1587 Elo2026-08-21
- LMArena WebDev
- 1587 Elo2026-08-30
- LMArena WebDev
- 1587 Elo2026-09-01
- Terminal-Bench 2.1‡
- 11.2%2026-08-13high effort
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 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Business WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Logic & Problem SolvingEstablished evidence
100% of intended weighted task evidence across 2 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. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Chat & RoleplayEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Creative WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Frontend & UIEstablished evidence
100% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Roleplay & CharacterEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Math & ReasoningEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for a General AssistantEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Agentic CodingEstablished evidence
82% of intended weighted task evidence across 5 independent sources. 8 of 8 configured evaluation feeds currently have results.
- Best LLM for Code CompletionEstablished evidence
81% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for Autonomous AgentsEstablished evidence
71% of intended weighted task evidence across 4 independent sources. 7 of 7 configured evaluation feeds currently have results.
- Best LLM for CodingEstablished evidence
68% of intended weighted task evidence across 4 independent sources. 8 of 8 configured evaluation feeds currently have results.
- Best Open-Weight LLM for Self-HostingEstablished evidence
67% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Fast SummariesEstablished evidence
64% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
- Best Value LLMEstablished evidence
64% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Literary TranslationProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from WMT translation. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Everyday TranslationProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from WMT translation. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for TranslationProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from WMT translation. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Hermes AgentProvisional evidence
51% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for OpenHandsProvisional evidence
51% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for GooseProvisional evidence
51% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for OpenClawProvisional evidence
51% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
- Best Cheap LLM for High VolumeProvisional evidence
50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Route reliability. 3 of 4 configured evaluation feeds currently have results.
- Cheapest Capable LLMProvisional evidence
50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Route reliability. 3 of 4 configured evaluation feeds currently have results.
- Best Local LLM for CodingProvisional evidence
50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for AI AgentsProvisional evidence
45% of intended weighted task evidence across 3 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or OSWorld Verified. 7 of 7 configured evaluation feeds currently have results.
- Best LLM for Debugging & Code ReviewProvisional evidence
40% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or SWE-bench Verified. 6 of 6 configured evaluation feeds currently have results.
- Best LLM for Document SummarizationProvisional evidence
40% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.
- Best LLM for SummarizationProvisional evidence
40% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.
- Best LLM for JSON & Schema OutputProvisional evidence
39% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Structured Data ExtractionProvisional evidence
39% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for High-Volume ExtractionProvisional evidence
31% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Route reliability or Structured-output eval. 2 of 4 configured evaluation feeds currently have results.
- Best LLM for Tool & Function CallingProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Search. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Massive ContextProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or LongBench v2. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Computer & Browser UseProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or OSWorld Verified. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for Image UnderstandingProvisional evidence
20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Vision or VLMEvalKit tasks. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for RAG & Long ContextProvisional evidence
18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results. Official release evidence is also tracked provisionally.
- Best LLM for OCR & DocumentsProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Vision & DocumentsProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results. Official release evidence is also tracked provisionally.
- Best LLM for Grounded RAGProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from CRAG or FACTS Grounding. 2 of 5 configured evaluation feeds currently have results.
- Best LLM for Charts & DiagramsProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Document ParsingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
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.
“It also achieves higher first-pass code accuracy and has improved performance in generating production-ready code as seen in FrontierCode 1.1 Main (43.6% vs 34.4%) and DeepSWE v1.1 (65.3% vs 49.0%).”
Google · Gemini 3.7 Flash: our most intelligent workhorse model“It outperforms 3.6 Flash on Arena.ai's WebDev Arena with an Elo score of 1588 vs 1538.”
Google · Gemini 3.7 Flash: our most intelligent workhorse model“It significantly outperforms 3.6 Flash on the GDP.pdf benchmark (34.0% vs 22.0%), an eval for testing a model's ability to process complex documents.”
Google · Gemini 3.7 Flash: our most intelligent workhorse model
Recommendation coverage
Where this model appears
Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.