Google model product
Gemini 3.5 Flash
5 Flash is Google's Flash-series large language model for coding and agentic workflows, with multimodal understanding, a 1 million-token input context window, 64k output tokens, and dynamic thinking by default.
Updated Oct 23, 2026. Default version: Gemini 3.5 Flash
LLMBoard Score75.2Gemini 3.5 Flash
Coverage80%15 benchmark families
Context window1MTokens
Official input price$1.5Google API
Gemini 3.5 Flash Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemini 3.5 Flash Benchmark Results
Benchmark scores for Gemini 3.5 Flash.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkBlueprint-Bench 2 | Score33.60% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro | Score83.60% | Rank02 | Participants73 | Percentile98.61% | EvidenceC | Evaluated |
| BenchmarkFinance Agent v2 | Score57.86% | Rank03 | Participants29 | Percentile92.86% | EvidenceB | Evaluated |
| BenchmarkARC-AGI v2 | Score72.10% | Rank05 | Participants19 | Percentile77.78% | EvidenceC | Evaluated |
| BenchmarkFinance Agent | Score57.90% | Rank05 | Participants8 | Percentile42.86% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score76.20% | Rank05 | Participants53 | Percentile92.31% | EvidenceC | Evaluated |
| BenchmarkMCP Atlas | Score83.60% | Rank06 | Participants39 | Percentile86.84% | EvidenceC | Evaluated |
| BenchmarkLiveBench instruction (2026-06-25) | Score75.60 score | Rank06 | Participants43 | Percentile88.10% | EvidenceB | EvaluatedN/A |
| BenchmarkLegal Agent Benchmark | Score0.80% | Rank10 | Participants15 | Percentile35.71% | EvidenceB | Evaluated |
| BenchmarkLM Arena Vision | Score1,308.33 rating | Rank11 | Participants113 | Percentile91.07% | EvidenceA | Evaluated |
| BenchmarkAA IFBench | Score76.33% | Rank12 | Participants168 | Percentile93.41% | EvidenceB | EvaluatedN/A |
| BenchmarkOSWorld-Verified | Score78.40% | Rank13 | Participants28 | Percentile55.56% | EvidenceC | Evaluated |
| BenchmarkToolathlon | Score56.50% | Rank13 | Participants42 | Percentile70.73% | EvidenceC | Evaluated |
| BenchmarkLiveBench | Score75.02% | Rank14 | Participants38 | Percentile64.86% | EvidenceB | Evaluated |
| BenchmarkLM Arena Text | Score1,481.98 rating | Rank14 | Participants218 | Percentile94.01% | EvidenceA | Evaluated |
| BenchmarkAA Omniscience Accuracy | Score51.40% | Rank15 | Participants201 | Percentile93.00% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Document | Score1,463.27 rating | Rank16 | Participants38 | Percentile59.46% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,476.92 rating | Rank16 | Participants131 | Percentile88.46% | EvidenceA | Evaluated |
| BenchmarkMRCR v2 (8-needle) | Score26.60% | Rank17 | Participants25 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkCharXiv-R | Score84.20% | Rank18 | Participants60 | Percentile71.19% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,282.39 rating | Rank19 | Participants113 | Percentile83.93% | EvidenceA | Evaluated |
| BenchmarkAA HLE Text No Tools | Score42.68% | Rank19 | Participants200 | Percentile90.95% | EvidenceB | EvaluatedN/A |
| BenchmarkAA SciCode Subtasks | Score53.94% | Rank20 | Participants89 | Percentile78.41% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Document Style Control | Score1,460.56 rating | Rank21 | Participants38 | Percentile45.95% | EvidenceA | Evaluated |
| BenchmarkAA GPQA Diamond | Score92.22% | Rank21 | Participants199 | Percentile89.90% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text Style Control | Score1,477.47 rating | Rank24 | Participants218 | Percentile89.40% | EvidenceA | Evaluated |
| BenchmarkLiveBench math (2026-06-25) | Score88.24 score | Rank24 | Participants43 | Percentile45.24% | EvidenceB | EvaluatedN/A |
| BenchmarkAA CritPt | Score13.14% | Rank29 | Participants200 | Percentile85.93% | EvidenceB | EvaluatedN/A |
| BenchmarkLiveBench reasoning (2026-06-25) | Score82.00 score | Rank29 | Participants43 | Percentile33.33% | EvidenceB | EvaluatedN/A |
| BenchmarkHumanity's Last Exam | Score40.20% | Rank39 | Participants109 | Percentile64.81% | EvidenceC | Evaluated |
Gemini 3.5 Flash Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categorypolish | Rank03 | Rating / score1,516.31 | Votes797 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank04 | Rating / score1,505.41 | Votes797 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank05 | Rating / score1,321.39 | Votes577 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank06 | Rating / score1,377.07 | Votes847 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank07 | Rating / score1,292.85 | Votes577 | ObservationsN/A | Result date |
| Arenatext factuality | Categorykorean | Rank08 | Rating / score1,444.20 | Votes453 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry medicine and healthcare | Rank09 | Rating / score1,507.03 | Votes3,010 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry writing and literature and language | Rank09 | Rating / score1,476.14 | Votes12,537 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank09 | Rating / score1,492.69 | Votes2,044 | ObservationsN/A | Result date |
| Arenatext factuality | Categorypolish | Rank09 | Rating / score1,468.62 | Votes345 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank10 | Rating / score1,504.21 | Votes2,388 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank10 | Rating / score1,507.25 | Votes1,218 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryjapanese | Rank10 | Rating / score1,458.94 | Votes381 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryrussian | Rank10 | Rating / score1,496.56 | Votes4,809 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank10 | Rating / score1,305.33 | Votes5,040 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank11 | Rating / score1,493.79 | Votes757 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank11 | Rating / score1,492.97 | Votes5,472 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycreative writing | Rank11 | Rating / score1,466.49 | Votes8,896 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry entertainment and sports and media | Rank11 | Rating / score1,462.11 | Votes11,722 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank11 | Rating / score1,316.63 | Votes9,712 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank11 | Rating / score1,308.33 | Votes13,862 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank11 | Rating / score1,346.42 | Votes847 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank12 | Rating / score1,477.70 | Votes12,667 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry legal and government | Rank12 | Rating / score1,501.56 | Votes3,484 | ObservationsN/A | Result date |
| Arenatext factuality | Categorynon english | Rank12 | Rating / score1,468.03 | Votes27,914 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank13 | Rating / score1,469.70 | Votes9,462 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank13 | Rating / score1,486.01 | Votes700 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank13 | Rating / score1,475.37 | Votes27,914 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry life and physical and social science | Rank13 | Rating / score1,504.93 | Votes7,372 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank13 | Rating / score1,323.35 | Votes3,618 | ObservationsN/A | Result date |
Gemini 3.5 Flash Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1.5 input, $9 output per 1M
- Official provider
- Lowest third-party
- From $0.1857 input, $1.11 output per 1M via UnoRouter
- Tracked offerings
- 37
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderUnoRouter | Provider model IDgemini-3.5-flash | Regionglobal | Input / 1M$0.1857 | Output / 1M$1.11 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDgemini-3.5-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDgoogle/gemini-3.5-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context1M | Updated |
| ProviderOrcaRouter | Provider model IDgoogle/gemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDgoogle/gemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderVertex | Provider model IDgemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderGoogle | Provider model IDgemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderImpossibl | Provider model IDgoogle/gemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDgoogle/gemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderCrossModel | Provider model IDgemini/gemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderNEAR AI Cloud | Provider model IDgoogle/gemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDgoogle/gemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderFastRouter | Provider model IDgoogle/gemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderZenMux | Provider model IDgoogle/gemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderSAP AI Core | Provider model IDgemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderOfox | Provider model IDgoogle/gemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderNeon | Provider model IDgemini-3-5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderOpenCode | Provider model IDgemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderRequesty | Provider model IDgemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDgoogle/gemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderEden AI | Provider model IDgoogle/gemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDgemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderGitHub Copilot | Provider model IDgemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context200K | Updated |
| ProviderPioneer | Provider model IDgemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderAbacus | Provider model IDgemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| Provider302.AI | Provider model IDgemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderOpper | Provider model IDgemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderTempr Gateway | Provider model IDgoogle/gemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderPrime Inference | Provider model IDgoogle/gemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderDatabricks | Provider model IDdatabricks-gemini-3-5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
Gemini 3.5 Flash Runtime Performance
Provider-specific output speed and catalog latency for Gemini 3.5 Flash. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Gemini 3.5 Flash Specifications
Technical details for the model's default version.
- Version
- Gemini 3.5 Flash
- Released
- May 19, 2026
- Knowledge cutoff
- Jan 31, 2026
- Parameters
- N/A
- Context window
- 1M
- Max output
- 1M
- Inputs
- audio, image, text, video
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Gemini 3.5 Flash Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGemini 3.5 Flash | Released | LLMBoard75.18 | ParametersN/A | Context1M | Max output1M | Open weightsNo | LicenseProprietary |
Models similar to Gemini 3.5 Flash
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemini 3.1 Pro
GOGoogle
Gemini 3.6 Flash
GOGoogle
Gemini 3.7 Flash
GOGoogle
Gemini 3.8 Flash
GOGoogle
Gemini 3 Pro
GOGoogle
Gemini 3 Flash
What is Gemini 3.5 Flash?
Key information about Gemini 3.5 Flash and its available data.
5 Flash is a Google large language model in the Flash series. It is designed for coding and complex agentic workflows and supports multimodal understanding, a 1 million-token input context window, 64k output tokens, and dynamic thinking by default.
Data as of 2026-10-22.
FAQ
Common questions about Gemini 3.5 Flash.
When was Gemini 3.5 Flash released?
Gemini 3.5 Flash's default version was released on May 19, 2026.
How much does Gemini 3.5 Flash cost?
Gemini 3.5 Flash's official API price is $1.5 per million input tokens and $9 per million output tokens via Google. The lowest tracked third-party offer starts at $0.1857 input and $1.11 output via UnoRouter.
Who created Gemini 3.5 Flash?
Gemini 3.5 Flash was created by Google.
What is the context window for Gemini 3.5 Flash?
The default version has a 1M token context window.
Is Gemini 3.5 Flash open weight?
No. The default version is not marked as having publicly available weights.