Google model product
Gemini 3 Flash
Gemini 3 Flash is a Google large language model with a 1 million-token input context window, optimized for agentic workflows, coding, and complex analysis.
Updated Sep 8, 2026. Default version: Gemini 3 Flash
LLMBoard Score64.3Gemini 3 Flash
Coverage40%24 benchmark families
Context window1MTokens
Official input price$0.50Google API
Gemini 3 Flash Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemini 3 Flash Benchmark Results
Benchmark scores for Gemini 3 Flash.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkGlobal PIQA | Score92.80% | Rank02 | Participants13 | Percentile91.67% | EvidenceC | Evaluated |
| Benchmarkt2-bench | Score90.20% | Rank02 | Participants23 | Percentile95.45% | EvidenceC | Evaluated |
| BenchmarkVideoMMMU | Score86.90% | Rank02 | Participants26 | Percentile96.00% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench Pro | Score2,316.00 points | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkMMMLU | Score91.80% | Rank04 | Participants49 | Percentile93.75% | EvidenceC | Evaluated |
| BenchmarkVending-Bench 2 | Score3,635.00 usd | Rank04 | Participants4 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score99.70% | Rank07 | Participants119 | Percentile94.92% | EvidenceC | Evaluated |
| BenchmarkSimpleQA | Score68.70% | Rank07 | Participants47 | Percentile86.96% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro | Score81.20% | Rank08 | Participants69 | Percentile89.71% | EvidenceC | Evaluated |
| BenchmarkFACTS Grounding | Score61.90% | Rank10 | Participants13 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkScreenSpot Pro | Score69.10% | Rank11 | Participants26 | Percentile60.00% | EvidenceC | Evaluated |
| BenchmarkLegal Agent Benchmark | Score0.00% | Rank12 | Participants13 | Percentile8.33% | EvidenceB | Evaluated |
| BenchmarkARC-AGI v2 | Score33.60% | Rank13 | Participants18 | Percentile29.41% | EvidenceC | Evaluated |
| BenchmarkFinance Agent v2 | Score42.55% | Rank14 | Participants26 | Percentile48.00% | EvidenceB | Evaluated |
| BenchmarkLM Arena Search | Score1,198.09 rating | Rank14 | Participants28 | Percentile51.85% | EvidenceA | Evaluated |
| BenchmarkLM Arena Search Factuality | Score1,180.48 rating | Rank16 | Participants28 | Percentile44.44% | EvidenceA | Evaluated |
| BenchmarkLM Arena Search Style Control | Score1,191.34 rating | Rank16 | Participants28 | Percentile44.44% | EvidenceA | Evaluated |
| BenchmarkOmniDocBench 1.5 | Score12.10% | Rank17 | Participants18 | Percentile5.88% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision | Score1,284.99 rating | Rank18 | Participants107 | Percentile83.96% | EvidenceA | Evaluated |
| BenchmarkMRCR v2 (8-needle) | Score22.10% | Rank20 | Participants24 | Percentile17.39% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score78.00% | Rank21 | Participants113 | Percentile82.14% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text | Score1,466.75 rating | Rank22 | Participants210 | Percentile89.95% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,272.48 rating | Rank22 | Participants107 | Percentile80.19% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,467.62 rating | Rank23 | Participants121 | Percentile81.67% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score90.40% | Rank24 | Participants247 | Percentile90.65% | EvidenceC | Evaluated |
| BenchmarkLiveBench | Score72.40% | Rank24 | Participants38 | Percentile37.84% | EvidenceB | Evaluated |
| BenchmarkToolathlon | Score49.40% | Rank24 | Participants41 | Percentile42.50% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,473.83 rating | Rank24 | Participants210 | Percentile89.00% | EvidenceA | Evaluated |
| BenchmarkLM Arena Document Style Control | Score1,440.79 rating | Rank25 | Participants33 | Percentile25.00% | EvidenceA | Evaluated |
| BenchmarkCharXiv-R | Score80.30% | Rank26 | Participants55 | Percentile53.70% | EvidenceC | Evaluated |
Gemini 3 Flash Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categoryentity recognition | Rank02 | Rating / score1,333.50 | Votes313 | ObservationsN/A | Result date |
| Arenavision style control | Categoryentity recognition | Rank02 | Rating / score1,288.51 | Votes313 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing | Rank03 | Rating / score1,306.36 | Votes217 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing | Rank03 | Rating / score1,289.10 | Votes217 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank05 | Rating / score1,496.72 | Votes564 | ObservationsN/A | Result date |
| Arenatext factuality | Categorypolish | Rank05 | Rating / score1,475.08 | Votes698 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank06 | Rating / score1,496.22 | Votes951 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank07 | Rating / score1,492.68 | Votes327 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank07 | Rating / score1,498.68 | Votes564 | ObservationsN/A | Result date |
| Arenavision | Categorycaptioning | Rank07 | Rating / score1,271.90 | Votes175 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank07 | Rating / score1,296.67 | Votes2,734 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank08 | Rating / score1,314.80 | Votes2,734 | ObservationsN/A | Result date |
| Arenavision style control | Categorycaptioning | Rank08 | Rating / score1,225.37 | Votes175 | ObservationsN/A | Result date |
| Arenatext factuality | Categorygerman | Rank09 | Rating / score1,448.77 | Votes851 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank09 | Rating / score1,498.07 | Votes951 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank10 | Rating / score1,491.75 | Votes327 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank11 | Rating / score1,291.75 | Votes1,286 | ObservationsN/A | Result date |
| Arenatext factuality | Categorykorean | Rank12 | Rating / score1,424.03 | Votes796 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycreative writing | Rank13 | Rating / score1,463.79 | Votes3,011 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank13 | Rating / score1,479.10 | Votes988 | ObservationsN/A | Result date |
| Arenasearch | Categoryoverall | Rank14 | Rating / score1,198.09 | Votes149,334 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank14 | Rating / score1,444.65 | Votes575 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank14 | Rating / score1,270.57 | Votes1,286 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank15 | Rating / score1,458.55 | Votes4,619 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank15 | Rating / score1,470.31 | Votes988 | ObservationsN/A | Result date |
| Arenatext factuality | Categorychinese | Rank15 | Rating / score1,515.78 | Votes1,353 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank15 | Rating / score1,445.43 | Votes575 | ObservationsN/A | Result date |
| Arenasearch factuality | Categoryoverall | Rank16 | Rating / score1,180.48 | Votes149,171 | ObservationsN/A | Result date |
| Arenasearch style control | Categoryoverall | Rank16 | Rating / score1,191.34 | Votes149,334 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryjapanese | Rank16 | Rating / score1,424.87 | Votes464 | ObservationsN/A | Result date |
Gemini 3 Flash Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.50 input, $3 output per 1M
- Official provider
- Lowest third-party
- From $0.07 input, $0.43 output per 1M via QiHang
- Tracked offerings
- 23
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderQiHang | Provider model IDgemini-3-flash-preview | Regionglobal | Input / 1M$0.07 | Output / 1M$0.43 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDgoogle/gemini-3-flash-preview | Regionglobal | Input / 1M$0.25 | Output / 1M$1.5 | Context1M | Updated |
| ProviderPoe | Provider model IDgoogle/gemini-3-flash | Regionglobal | Input / 1M$0.40 | Output / 1M$2.4 | Context1M | Updated |
| ProviderOrcaRouter | Provider model IDgoogle/gemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDgoogle/gemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderVertex | Provider model IDgemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderGoogle | Provider model IDgemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderJiekou.AI | Provider model IDgemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDgoogle/gemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDgoogle/gemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderZenMux | Provider model IDgoogle/gemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderPerplexity Agent | Provider model IDgoogle/gemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderOfox | Provider model IDgoogle/gemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| Provider302.AI | Provider model IDgemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderOpenCode Zen | Provider model IDgemini-3-flash | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderFrogBot | Provider model IDgemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDgemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDgoogle/gemini-3-flash | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderEden AI | Provider model IDgoogle/gemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDgemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderAbacus | Provider model IDgemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderVenice AI | Provider model IDgemini-3-flash-preview | Regionglobal | Input / 1M$0.70 | Output / 1M$3.75 | Context256K | Updated |
Gemini 3 Flash Runtime Performance
Provider-specific output speed and catalog latency for Gemini 3 Flash. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderGoogle | Output Speed124.32 tok/s | Catalog Latency4.60 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.
Gemini 3 Flash Specifications
Technical details for the model's default version.
- Version
- Gemini 3 Flash
- Released
- Dec 17, 2025
- Knowledge cutoff
- Jan 31, 2025
- Parameters
- N/A
- Context window
- 1M
- Max output
- 65.5K
- Inputs
- audio, image, text, video
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Gemini 3 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 Flash | Released | LLMBoard64.29 | ParametersN/A | Context1M | Max output65.5K | Open weightsNo | LicenseProprietary |
Models similar to Gemini 3 Flash
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemini 3.5 Flash Cyber
GOGoogle
Gemini 3 Pro
GOGoogle
Gemini 3.8 Flash Cyber
GOGoogle
Gemma 4 31B
GOGoogle
Gemini 3.5 Flash Lite
GOGoogle
Gemini 3.6 Flash
What is Gemini 3 Flash?
Key information about Gemini 3 Flash and its available data.
Gemini 3 Flash is a large language model from Google. It combines Gemini 3's Pro-grade reasoning with Flash-level latency, efficiency, and cost, and has a 1 million-token input context window.
Data as of 2026-09-08.
FAQ
Common questions about Gemini 3 Flash.
When was Gemini 3 Flash released?
Gemini 3 Flash's default version was released on Dec 17, 2025.
How much does Gemini 3 Flash cost?
Gemini 3 Flash's official API price is $0.50 per million input tokens and $3 per million output tokens via Google. The lowest tracked third-party offer starts at $0.07 input and $0.43 output via QiHang.
Who created Gemini 3 Flash?
Gemini 3 Flash was created by Google.
What is the context window for Gemini 3 Flash?
The default version has a 1M token context window.
Is Gemini 3 Flash open weight?
No. The default version is not marked as having publicly available weights.