Google model product
Gemini 3.6 Flash
6 Flash is a multimodal reasoning model from Google for agentic coding, knowledge work, and spatial reasoning.
Updated Oct 23, 2026. Default version: Gemini 3.6 Flash
LLMBoard Score74.6Gemini 3.6 Flash
Coverage80%6 benchmark families
Context window1MTokens
Official input price$0.75Google API
Gemini 3.6 Flash Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemini 3.6 Flash Benchmark Results
Benchmark scores for Gemini 3.6 Flash.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMLE-Bench | Score63.90% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkOSWorld-Verified | Score83.00% | Rank05 | Participants28 | Percentile85.19% | EvidenceC | Evaluated |
| BenchmarkCharXiv-R | Score89.40% | Rank08 | Participants60 | Percentile88.14% | EvidenceC | Evaluated |
| BenchmarkLiveBench instruction (2026-06-25) | Score75.37 score | Rank08 | Participants43 | Percentile83.33% | EvidenceB | EvaluatedN/A |
| BenchmarkMRCR v2 (8-needle) | Score54.00% | Rank10 | Participants25 | Percentile62.50% | EvidenceC | Evaluated |
| BenchmarkAA GPQA Diamond | Score92.83% | Rank15 | Participants199 | Percentile92.93% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text | Score1,479.53 rating | Rank16 | Participants218 | Percentile93.09% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,298.88 rating | Rank16 | Participants113 | Percentile86.61% | EvidenceA | Evaluated |
| BenchmarkAA Omniscience Accuracy | Score49.97% | Rank17 | Participants201 | Percentile92.00% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text Style Control | Score1,483.01 rating | Rank18 | Participants218 | Percentile92.17% | EvidenceA | Evaluated |
| BenchmarkLM Arena Document | Score1,456.06 rating | Rank19 | Participants38 | Percentile51.35% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,281.98 rating | Rank20 | Participants113 | Percentile83.04% | EvidenceA | Evaluated |
| BenchmarkAA SciCode Subtasks | Score53.36% | Rank22 | Participants89 | Percentile76.14% | EvidenceB | EvaluatedN/A |
| BenchmarkLiveBench reasoning (2026-06-25) | Score85.15 score | Rank22 | Participants43 | Percentile50.00% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text Factuality | Score1,471.68 rating | Rank23 | Participants131 | Percentile83.08% | EvidenceA | Evaluated |
| BenchmarkLM Arena Document Style Control | Score1,453.42 rating | Rank24 | Participants38 | Percentile37.84% | EvidenceA | Evaluated |
| BenchmarkSWE-Bench Pro | Score58.70% | Rank25 | Participants63 | Percentile61.29% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.1 | Score78.00% | Rank26 | Participants48 | Percentile46.81% | EvidenceC | Evaluated |
| BenchmarkAA LCR v1.1 | Score80.00% | Rank27 | Participants193 | Percentile86.46% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score40.82% | Rank27 | Participants200 | Percentile86.93% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Agent Bash Reliability No Prereq | Score0.52% | Rank28 | Participants45 | Percentile38.64% | EvidenceA | Evaluated |
| BenchmarkLiveBench math (2026-06-25) | Score86.40 score | Rank30 | Participants43 | Percentile30.95% | EvidenceB | EvaluatedN/A |
| BenchmarkAA CritPt | Score10.57% | Rank33 | Participants200 | Percentile83.92% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Webdev | Score1,538.05 rating | Rank34 | Participants107 | Percentile68.87% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Bash Recovery Steps | Score-18.23% | Rank40 | Participants44 | Percentile9.30% | EvidenceA | Evaluated |
| BenchmarkDeepSWE 1.1 | Score49.00% | Rank43 | Participants51 | Percentile16.00% | EvidenceB | Evaluated |
Gemini 3.6 Flash Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categoryfrench | Rank06 | Rating / score1,502.91 | Votes1,149 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank08 | Rating / score1,512.25 | Votes913 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryspanish | Rank08 | Rating / score1,480.92 | Votes737 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank09 | Rating / score1,507.55 | Votes1,760 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank09 | Rating / score1,512.53 | Votes1,149 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank09 | Rating / score1,504.43 | Votes1,760 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank12 | Rating / score1,471.08 | Votes7,574 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank13 | Rating / score1,488.98 | Votes1,481 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank14 | Rating / score1,487.97 | Votes4,172 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank14 | Rating / score1,311.58 | Votes6,075 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank14 | Rating / score1,300.74 | Votes6,075 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank15 | Rating / score1,465.63 | Votes7,574 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank15 | Rating / score1,474.83 | Votes629 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank16 | Rating / score1,530.71 | Votes2,690 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank16 | Rating / score1,481.85 | Votes15,141 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank16 | Rating / score1,479.53 | Votes36,079 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank16 | Rating / score1,475.82 | Votes947 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank16 | Rating / score1,460.91 | Votes9,301 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank16 | Rating / score1,473.78 | Votes9,845 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank16 | Rating / score1,356.93 | Votes536 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank16 | Rating / score1,294.79 | Votes3,098 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank16 | Rating / score1,288.86 | Votes427 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank16 | Rating / score1,298.88 | Votes8,979 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank16 | Rating / score1,334.62 | Votes536 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank17 | Rating / score1,488.14 | Votes26,881 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank17 | Rating / score1,480.46 | Votes592 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank17 | Rating / score1,455.98 | Votes9,301 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryrussian | Rank17 | Rating / score1,487.08 | Votes3,681 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank17 | Rating / score1,530.27 | Votes2,690 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank17 | Rating / score1,492.90 | Votes4,172 | ObservationsN/A | Result date |
Gemini 3.6 Flash Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.75 input, $3.75 output per 1M
- Official provider
- Lowest third-party
- From $0.3429 input, $1.71 output per 1M via Kenari
- Tracked offerings
- 32
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderKenari | Provider model IDgemini-3-6-flash | Regionglobal | Input / 1M$0.3429 | Output / 1M$1.71 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDgoogle/gemini-3.6-flash | Regionglobal | Input / 1M$0.375 | Output / 1M$1.88 | Context1M | Updated |
| ProviderOrcaRouter | Provider model IDgoogle/gemini-3.6-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderCortecs | Provider model IDgemini-3.6-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDgoogle/gemini-3.6-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderVertex | Provider model IDgemini-3.6-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderGoogle | Provider model IDgemini-3.6-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderImpossibl | Provider model IDgoogle/gemini-3.6-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDgoogle/gemini-3.6-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderCrossModel | Provider model IDgemini/gemini-3.6-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderOfox | Provider model IDgoogle/gemini-3.6-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDgoogle/gemini-3.6-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderEden AI | Provider model IDgoogle/gemini-3.6-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDgemini-3.6-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderGitHub Copilot | Provider model IDgemini-3.6-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderAbacus | Provider model IDgemini-3.6-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderTempr Gateway | Provider model IDgoogle/gemini-3.6-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDgemini-3.6-flash | Regionglobal | Input / 1M$0.75 | Output / 1M$3.75 | Context1M | Updated |
| ProviderPoe | Provider model IDgoogle/gemini-3.6-flash | Regionglobal | Input / 1M$0.7576 | Output / 1M$3.79 | Context1M | Updated |
| ProviderVenice AI | Provider model IDgemini-3-6-flash | Regionglobal | Input / 1M$0.9375 | Output / 1M$4.69 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDgoogle/gemini-3.6-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderNeon | Provider model IDgemini-3-6-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderOpenCode | Provider model IDgemini-3.6-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderRequesty | Provider model IDgemini-3.6-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$7 | Context1M | Updated |
| ProviderPioneer | Provider model IDgemini-3.6-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| Provider302.AI | Provider model IDgemini-3.6-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderAI/ML API | Provider model IDgoogle/gemini-3.6-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderPrime Inference | Provider model IDgoogle/gemini-3.6-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderCommandCode | Provider model IDgoogle/gemini-3.6-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderPerplexity Agent | Provider model IDgoogle/gemini-3.6-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
Gemini 3.6 Flash Runtime Performance
Provider-specific output speed and catalog latency for Gemini 3.6 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 3.6 Flash Specifications
Technical details for the model's default version.
- Version
- Gemini 3.6 Flash
- Released
- Jul 21, 2026
- Knowledge cutoff
- Mar 31, 2026
- Parameters
- N/A
- Context window
- 1M
- Max output
- 65.5K
- Inputs
- audio, image, text, video
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Gemini 3.6 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 3.6 Flash | Released | LLMBoard74.58 | ParametersN/A | Context1M | Max output65.5K | Open weightsNo | LicenseProprietary |
Models similar to Gemini 3.6 Flash
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemini 3.5 Flash
GOGoogle
Gemini 3.1 Pro
GOGoogle
Gemini 3.7 Flash
GOGoogle
Gemini 3.8 Flash
GOGoogle
Gemini 3 Pro
GOGoogle
Gemini 3 Flash
What is Gemini 3.6 Flash?
Key information about Gemini 3.6 Flash and its available data.
6 Flash is a Google large language model that accepts text, image, video, audio, and PDF inputs. It has a 1 million-token context window and supports up to 65,536 output tokens.
Data as of 2026-10-22.
FAQ
Common questions about Gemini 3.6 Flash.
When was Gemini 3.6 Flash released?
Gemini 3.6 Flash's default version was released on Jul 21, 2026.
How much does Gemini 3.6 Flash cost?
Gemini 3.6 Flash's official API price is $0.75 per million input tokens and $3.75 per million output tokens via Google. The lowest tracked third-party offer starts at $0.3429 input and $1.71 output via Kenari.
Who created Gemini 3.6 Flash?
Gemini 3.6 Flash was created by Google.
What is the context window for Gemini 3.6 Flash?
The default version has a 1M token context window.
Is Gemini 3.6 Flash open weight?
No. The default version is not marked as having publicly available weights.