Google model product
5 Flash is Google's strongest agentic and coding model in the Flash series, delivering frontier-level performance at up to 4x the speed of comparable frontier models and often at less than half the cost.
Updated Aug 17, 2026. Default version: Gemini 3.5 Flash
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Gemini 3.5 Flash.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkFinance Agent v2 | Score57.9% | Rank01 | Participants26 | Percentile100.0% | EvidenceB | Evaluated |
| BenchmarkMMMU-Pro | Score83.6% | Rank01 | Participants68 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkBlueprint-Bench 2 | Score33.6% | Rank02 | Participants2 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkARC-AGI v2 | Score72.1% | Rank04 | Participants17 | Percentile81.3% | EvidenceC | Evaluated |
| BenchmarkMCP Atlas | Score83.6% | Rank04 | Participants33 | Percentile90.6% | EvidenceC | Evaluated |
| BenchmarkFinance Agent | Score57.9% | Rank05 | Participants8 | Percentile42.9% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score76.2% | Rank05 | Participants51 | Percentile92.0% | EvidenceC | Evaluated |
| BenchmarkLegal Agent Benchmark | Score0.8% | Rank08 | Participants13 | Percentile41.7% | EvidenceB | Evaluated |
| BenchmarkToolathlon | Score56.5% | Rank09 | Participants37 | Percentile77.8% | EvidenceC | Evaluated |
| BenchmarkOSWorld-Verified | Score78.4% | Rank10 | Participants24 | Percentile60.9% | EvidenceC | Evaluated |
| BenchmarkCharXiv-R | Score84.2% | Rank14 | Participants51 | Percentile74.0% | EvidenceC | Evaluated |
| BenchmarkLiveBench | Score75.0% | Rank14 | Participants38 | Percentile64.9% | EvidenceB | Evaluated |
| BenchmarkMRCR v2 (8-needle) | Score26.6% | Rank15 | Participants23 | Percentile36.4% | EvidenceC | Evaluated |
| BenchmarkDeepSWE 1.1 | Score37.0% | Rank22 | Participants25 | Percentile12.5% | EvidenceB | Evaluated |
| BenchmarkSWE-Bench Pro | Score55.1% | Rank35 | Participants50 | Percentile30.6% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score40.2% | Rank36 | Participants99 | Percentile64.3% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categoryoverall | Rank09 | Rating / score1309.1 | Votes5,762 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank10 | Rating / score1481.6 | Votes25,746 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank10 | Rating / score1307.6 | Votes5,616 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank12 | Rating / score1480.0 | Votes25,720 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank15 | Rating / score1284.0 | Votes5,616 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank16 | Rating / score1476.1 | Votes23,928 | ObservationsN/A | Result date |
| Arenadocument | Categoryoverall | Rank17 | Rating / score1464.6 | Votes3,689 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank17 | Rating / score1282.8 | Votes5,762 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank19 | Rating / score1477.2 | Votes25,746 | ObservationsN/A | Result date |
| Arenadocument style control | Categoryoverall | Rank20 | Rating / score1462.3 | Votes3,689 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank23 | Rating / score1474.9 | Votes23,928 | ObservationsN/A | Result date |
| Arenaagent task outcome explicit | Categoryoverall | Rank25 | Rating / score0.0 | VotesN/A | Observations67.3K | Result date |
| Arenatext factuality | Categoryoverall | Rank26 | Rating / score1466.2 | Votes23,897 | ObservationsN/A | Result date |
| Arenaagent steerability | Categoryoverall | Rank28 | Rating / score-0.0 | VotesN/A | Observations100.1K | Result date |
| Arenaagent | Categoryoverall | Rank29 | Rating / score-0.0 | VotesN/A | Observations4M | Result date |
| Arenaagent praise complaint | Categoryoverall | Rank29 | Rating / score-0.0 | VotesN/A | Observations25.8K | Result date |
| Arenawebdev | Categoryoverall | Rank32 | Rating / score1499.4 | Votes6,840 | ObservationsN/A | Result date |
| Arenaagent bash recovery steps | Categoryoverall | Rank33 | Rating / score-0.0 | VotesN/A | Observations20.9K | Result date |
| Arenaagent praise complaint | Categoryoverall | Rank35 | Rating / score-0.1 | VotesN/A | Observations3.7K | Result date |
| Arenaagent steerability | Categoryoverall | Rank35 | Rating / score-0.0 | VotesN/A | Observations15.2K | Result date |
| Arenaagent tool hallucination | Categoryoverall | Rank35 | Rating / score0.0 | VotesN/A | Observations460.9K | Result date |
| Arenawebdev | Categoryoverall | Rank35 | Rating / score1488.6 | Votes9,351 | ObservationsN/A | Result date |
| Arenaagent bash recovery steps | Categoryoverall | Rank36 | Rating / score-0.0 | VotesN/A | Observations159.7K | Result date |
| Arenaagent tool hallucination | Categoryoverall | Rank37 | Rating / score0.0 | VotesN/A | Observations3.7M | Result date |
| Arenaagent | Categoryoverall | Rank38 | Rating / score-0.0 | VotesN/A | Observations510.4K | Result date |
| Arenaagent task outcome explicit | Categoryoverall | Rank41 | Rating / score-0.1 | VotesN/A | Observations9.8K | Result date |
Official vendor API pricing appears first, followed by individual provider offers.
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 |
| 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 Zen | Provider model IDgemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderAIHubMix | 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 |
| ProviderEden AI | Provider model IDvertex/gemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | Updated |
| ProviderLLM 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 |
| ProviderKilo Gateway | Provider model IDgoogle/gemini-3.5-flash | Regionglobal | Input / 1M$1.5 | Output / 1M$9 | Context1M | 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 |
| ProviderPoe | Provider model IDgoogle/gemini-3.5-flash | Regionglobal | Input / 1M$1.52 | Output / 1M$9.09 | Context1M | Updated |
| ProviderXpersona | Provider model IDgemini-3.5-flash | Regionglobal | Input / 1M$1.55 | Output / 1M$12.2 | Context1M | Updated |
| ProviderVenice AI | Provider model IDgemini-3-5-flash | Regionglobal | Input / 1M$1.55 | Output / 1M$9.45 | Context1M | Updated |
| ProviderCortecs | Provider model IDgemini-3.5-flash | Regionglobal | Input / 1M$1.65 | Output / 1M$9.9 | Context1M | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Provider-specific output speed and catalog latency for Gemini 3.5 Flash. Runtime does not affect the capability score.
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderGoogle | Output Speed1.218 tok/s | Catalog Latency1.68 s | Max Input1M | Max Output65.5K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGemini 3.5 Flash | Released | LLMBoard78.4 | ParametersN/A | Context1M | Max output65.5K | Open weightsNo | LicenseProprietary |
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about Gemini 3.5 Flash and its available data.
5 Flash is Google's strongest agentic and coding model in the Flash series, delivering frontier-level performance at up to 4x the speed of comparable frontier models and often at less than half the cost. 1 Pro on coding and agentic benchmarks while leading in multimodal understanding.
It supports a 1 million-token input context window with 64k output tokens and uses dynamic thinking by default.
Data as of 2026-08-17.
Common questions about Gemini 3.5 Flash.
Gemini 3.5 Flash's default version was released on May 19, 2026.
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.
Gemini 3.5 Flash was created by Google.
The default version has a 1M token context window.
No. The default version is not marked as having publicly available weights.
28 provider offerings are linked to the default version.
Nearby ranked alternatives include Claude Opus 4.6, Grok 4.6, Seed 2.1 Pro.