Google model product
Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost.
Updated Aug 17, 2026. Default version: Gemini 3 Flash
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Gemini 3 Flash.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkGlobal PIQA | Score92.8% | Rank02 | Participants13 | Percentile91.7% | EvidenceC | Evaluated |
| Benchmarkt2-bench | Score90.2% | Rank02 | Participants23 | Percentile95.5% | EvidenceC | Evaluated |
| BenchmarkVideoMMMU | Score86.9% | Rank02 | Participants26 | Percentile96.0% | EvidenceC | Evaluated |
| BenchmarkMMMLU | Score91.8% | Rank03 | Participants49 | Percentile95.8% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench Pro | Score2,316 points | Rank04 | Participants4 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkVending-Bench 2 | Score3,635 usd | Rank04 | Participants4 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score99.7% | Rank07 | Participants115 | Percentile94.7% | EvidenceC | Evaluated |
| BenchmarkSimpleQA | Score68.7% | Rank07 | Participants47 | Percentile87.0% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro | Score81.2% | Rank08 | Participants68 | Percentile89.5% | EvidenceC | Evaluated |
| BenchmarkFACTS Grounding | Score61.9% | Rank10 | Participants13 | Percentile25.0% | EvidenceC | Evaluated |
| BenchmarkLegal Agent Benchmark | Score0.0% | Rank10 | Participants13 | Percentile25.0% | EvidenceB | Evaluated |
| BenchmarkScreenSpot Pro | Score69.1% | Rank10 | Participants25 | Percentile62.5% | EvidenceC | Evaluated |
| BenchmarkARC-AGI v2 | Score33.6% | Rank12 | Participants17 | Percentile31.3% | EvidenceC | Evaluated |
| BenchmarkFinance Agent v2 | Score42.5% | Rank14 | Participants26 | Percentile48.0% | EvidenceB | Evaluated |
| BenchmarkOmniDocBench 1.5 | Score12.1% | Rank17 | Participants18 | Percentile5.9% | EvidenceC | Evaluated |
| BenchmarkMRCR v2 (8-needle) | Score22.1% | Rank19 | Participants23 | Percentile18.2% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score90.4% | Rank20 | Participants239 | Percentile92.0% | EvidenceC | Evaluated |
| BenchmarkToolathlon | Score49.4% | Rank20 | Participants37 | Percentile47.2% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score78.0% | Rank21 | Participants111 | Percentile81.8% | EvidenceC | Evaluated |
| BenchmarkCharXiv-R | Score80.3% | Rank22 | Participants51 | Percentile58.0% | EvidenceC | Evaluated |
| BenchmarkLiveBench | Score72.4% | Rank24 | Participants38 | Percentile37.8% | EvidenceB | Evaluated |
| BenchmarkHumanity's Last Exam | Score43.5% | Rank31 | Participants99 | Percentile69.4% | EvidenceC | Evaluated |
| BenchmarkMCP Atlas | Score57.4% | Rank31 | Participants33 | Percentile6.3% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score47.6% | Rank38 | Participants51 | Percentile26.0% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenasearch | Categoryoverall | Rank13 | Rating / score1197.3 | Votes125,928 | ObservationsN/A | Result date |
| Arenasearch factuality | Categoryoverall | Rank17 | Rating / score1180.2 | Votes125,762 | ObservationsN/A | Result date |
| Arenasearch style control | Categoryoverall | Rank17 | Rating / score1190.2 | Votes125,928 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank23 | Rating / score1466.9 | Votes30,246 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank24 | Rating / score1466.0 | Votes30,859 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank24 | Rating / score1283.4 | Votes35,759 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank28 | Rating / score1472.9 | Votes30,859 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank28 | Rating / score1270.8 | Votes35,759 | ObservationsN/A | Result date |
| Arenadocument style control | Categoryoverall | Rank29 | Rating / score1440.8 | Votes7,173 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank33 | Rating / score1259.0 | Votes34,207 | ObservationsN/A | Result date |
| Arenaagent steerability | Categoryoverall | Rank34 | Rating / score-0.0 | VotesN/A | Observations89.6K | Result date |
| Arenadocument | Categoryoverall | Rank34 | Rating / score1413.3 | Votes7,173 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank35 | Rating / score1264.6 | Votes34,207 | ObservationsN/A | Result date |
| Arenaagent task outcome explicit | Categoryoverall | Rank40 | Rating / score-0.1 | VotesN/A | Observations61.2K | Result date |
| Arenaagent praise complaint | Categoryoverall | Rank41 | Rating / score-0.1 | VotesN/A | Observations22.4K | Result date |
| Arenaagent | Categoryoverall | Rank42 | Rating / score-0.1 | VotesN/A | Observations1.9M | Result date |
| Arenaagent tool hallucination | Categoryoverall | Rank43 | Rating / score-0.0 | VotesN/A | Observations1.6M | Result date |
| Arenaagent bash recovery steps | Categoryoverall | Rank45 | Rating / score-0.2 | VotesN/A | Observations83K | Result date |
| Arenatext style control | Categoryoverall | Rank49 | Rating / score1458.1 | Votes86,485 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank49 | Rating / score1437.9 | Votes10,472 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank51 | Rating / score1451.3 | Votes85,728 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank55 | Rating / score1442.1 | Votes86,485 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank73 | Rating / score1382.7 | Votes20,940 | ObservationsN/A | Result date |
Official vendor API pricing appears first, followed by individual provider offers.
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 |
| 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 |
| ProviderLLM Gateway | Provider model IDgemini-3-flash-preview | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDgoogle/gemini-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 |
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 Flash. Runtime does not affect the capability score.
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderGoogle | Output Speed65.14 tok/s | Catalog Latency5.259 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 Flash | Released | LLMBoard64.6 | 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 Flash and its available data.
Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost. It combines Gemini 3's Pro-grade reasoning with Flash-level latency, efficiency and cost. Features a 1 million-token input context window and is optimized for agentic workflows, coding, and complex analysis.
Data as of 2026-08-17.
Common questions about Gemini 3 Flash.
Gemini 3 Flash's default version was released on Dec 17, 2025.
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.
Gemini 3 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.
23 provider offerings are linked to the default version.
Nearby ranked alternatives include Qwen3.5 397B A17B, Kimi K2.5, Inkling Small.