Google model product
Gemini 3.1 Flash Lite
1 Flash Lite is a Google large language model for high-volume, latency-sensitive tasks such as translation, content moderation, and classification.
Updated Oct 23, 2026. Default version: Gemini 3.1 Flash-Lite
LLMBoard Score50.3Gemini 3.1 Flash-Lite
Coverage60%11 benchmark families
Context window1MTokens
Official input price$0.25Google API
Gemini 3.1 Flash Lite Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemini 3.1 Flash Lite Benchmark Results
Benchmark scores for Gemini 3.1 Flash-Lite.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkVideoMMMU | Score84.80% | Rank06 | Participants28 | Percentile81.48% | EvidenceC | Evaluated |
| BenchmarkMRCR v2 (8-needle) | Score60.10% | Rank09 | Participants25 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkAA IFBench | Score77.21% | Rank10 | Participants168 | Percentile94.61% | EvidenceB | EvaluatedN/A |
| BenchmarkFACTS Grounding | Score40.60% | Rank12 | Participants13 | Percentile8.33% | EvidenceC | Evaluated |
| BenchmarkLegal Agent Benchmark | Score0.00% | Rank12 | Participants15 | Percentile21.43% | EvidenceB | Evaluated |
| BenchmarkMMMLU | Score88.90% | Rank15 | Participants51 | Percentile72.00% | EvidenceC | Evaluated |
| BenchmarkSimpleQA | Score43.30% | Rank19 | Participants47 | Percentile60.87% | EvidenceC | Evaluated |
| BenchmarkFinance Agent v2 | Score29.99% | Rank27 | Participants29 | Percentile7.14% | EvidenceB | Evaluated |
| BenchmarkMMMU-Pro | Score76.80% | Rank27 | Participants73 | Percentile63.89% | EvidenceC | Evaluated |
| BenchmarkCharXiv-R | Score73.20% | Rank41 | Participants60 | Percentile32.20% | EvidenceC | Evaluated |
| BenchmarkAA Omniscience Accuracy | Score36.27% | Rank46 | Participants201 | Percentile77.50% | EvidenceB | EvaluatedN/A |
| BenchmarkAA SciCode Subtasks | Score43.40% | Rank52 | Participants89 | Percentile42.05% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Vision Style Control | Score1,234.63 rating | Rank54 | Participants113 | Percentile52.68% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score86.90% | Rank57 | Participants256 | Percentile78.04% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision | Score1,240.18 rating | Rank59 | Participants113 | Percentile48.21% | EvidenceA | Evaluated |
| BenchmarkAA LCR v1.1 | Score74.33% | Rank65 | Participants193 | Percentile66.67% | EvidenceB | EvaluatedN/A |
| BenchmarkHumanity's Last Exam | Score16.00% | Rank82 | Participants109 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,432.90 rating | Rank83 | Participants218 | Percentile62.21% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,432.94 rating | Rank84 | Participants131 | Percentile36.15% | EvidenceA | Evaluated |
| BenchmarkAA CritPt | Score1.14% | Rank88 | Participants200 | Percentile56.28% | EvidenceB | EvaluatedN/A |
| BenchmarkAA GPQA Diamond | Score82.22% | Rank89 | Participants199 | Percentile55.56% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Webdev | Score1,256.55 rating | Rank97 | Participants107 | Percentile9.43% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,415.79 rating | Rank98 | Participants218 | Percentile55.30% | EvidenceA | Evaluated |
| BenchmarkAA HLE Text No Tools | Score17.19% | Rank98 | Participants200 | Percentile51.26% | EvidenceB | EvaluatedN/A |
Gemini 3.1 Flash Lite 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 | Rank04 | Rating / score1,307.59 | Votes259 | ObservationsN/A | Result date |
| Arenavision style control | Categoryentity recognition | Rank04 | Rating / score1,271.11 | Votes259 | ObservationsN/A | Result date |
| Arenavision style control | Categorycaptioning | Rank08 | Rating / score1,225.48 | Votes73 | ObservationsN/A | Result date |
| Arenavision | Categorycaptioning | Rank10 | Rating / score1,259.45 | Votes73 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryjapanese | Rank23 | Rating / score1,420.40 | Votes442 | ObservationsN/A | Result date |
| Arenatext factuality | Categorypolish | Rank26 | Rating / score1,435.43 | Votes848 | ObservationsN/A | Result date |
| Arenatext factuality | Categorykorean | Rank29 | Rating / score1,401.51 | Votes630 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank31 | Rating / score1,265.86 | Votes979 | ObservationsN/A | Result date |
| Arenatext factuality | Categorygerman | Rank32 | Rating / score1,396.95 | Votes659 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank32 | Rating / score1,250.21 | Votes979 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank42 | Rating / score1,236.66 | Votes1,883 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank44 | Rating / score1,442.99 | Votes1,266 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank45 | Rating / score1,247.63 | Votes1,883 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank48 | Rating / score1,413.09 | Votes647 | ObservationsN/A | Result date |
| Arenawebdev | Categoryimage to webdev | Rank48 | Rating / score1,336.40 | Votes6,518 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryspanish | Rank49 | Rating / score1,435.55 | Votes1,545 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank49 | Rating / score1,270.33 | Votes1,989 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank49 | Rating / score1,271.20 | Votes3,947 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank51 | Rating / score1,453.35 | Votes1,266 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank51 | Rating / score1,270.69 | Votes3,947 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank52 | Rating / score1,277.74 | Votes1,989 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank53 | Rating / score1,421.08 | Votes647 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank54 | Rating / score1,246.91 | Votes19,353 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank54 | Rating / score1,234.63 | Votes27,657 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank55 | Rating / score1,451.00 | Votes1,651 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank58 | Rating / score1,245.94 | Votes19,353 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank59 | Rating / score1,240.18 | Votes27,657 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank59 | Rating / score1,251.55 | Votes7,269 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry legal and government | Rank60 | Rating / score1,452.71 | Votes3,928 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank60 | Rating / score1,226.46 | Votes11,005 | ObservationsN/A | Result date |
Gemini 3.1 Flash Lite Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.25 input, $1.5 output per 1M
- Official provider
- Lowest third-party
- From $0.125 input, $0.75 output per 1M via Kilo Gateway
- Tracked offerings
- 12
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderKilo Gateway | Provider model IDgoogle/gemini-3.1-flash-lite-preview | Regionglobal | Input / 1M$0.125 | Output / 1M$0.75 | Context1M | Updated |
| ProviderOrcaRouter | Provider model IDgoogle/gemini-3.1-flash-lite-preview | Regionglobal | Input / 1M$0.25 | Output / 1M$1.5 | Context1M | Updated |
| ProviderGoogle | Provider model IDgemini-3.1-flash-lite | Regionglobal | Input / 1M$0.25 | Output / 1M$1.5 | Context1M | Updated |
| ProviderGoogle | Provider model IDgemini-3.1-flash-lite-preview | Regionglobal | Input / 1M$0.25 | Output / 1M$1.5 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDgoogle/gemini-3.1-flash-lite-preview | Regionglobal | Input / 1M$0.25 | Output / 1M$1.5 | Context1M | Updated |
| ProviderVivgrid | Provider model IDgemini-3.1-flash-lite-preview | Regionglobal | Input / 1M$0.25 | Output / 1M$1.5 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDgoogle/gemini-3.1-flash-lite-preview | Regionglobal | Input / 1M$0.25 | Output / 1M$1.5 | Context1M | Updated |
| ProviderZenMux | Provider model IDgoogle/gemini-3.1-flash-lite-preview | Regionglobal | Input / 1M$0.25 | Output / 1M$1.5 | Context1.1M | Updated |
| ProviderEden AI | Provider model IDgoogle/gemini-3.1-flash-lite-preview | Regionglobal | Input / 1M$0.25 | Output / 1M$1.5 | Context1M | Updated |
| ProviderAbacus | Provider model IDgemini-3.1-flash-lite-preview | Regionglobal | Input / 1M$0.25 | Output / 1M$1.5 | Context1M | Updated |
| Provider302.AI | Provider model IDgemini-3.1-flash-lite-preview | Regionglobal | Input / 1M$0.25 | Output / 1M$1.5 | Context1M | Updated |
| ProviderAI/ML API | Provider model IDgoogle/gemini-3.1-flash-lite-preview | Regionglobal | Input / 1M$0.2645 | Output / 1M$1.59 | Context1M | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Gemini 3.1 Flash Lite Runtime Performance
Provider-specific output speed and catalog latency for Gemini 3.1 Flash-Lite. 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 3.1 Flash Lite Specifications
Technical details for the model's default version.
- Version
- Gemini 3.1 Flash-Lite
- Released
- Mar 3, 2026
- Knowledge cutoff
- Jan 31, 2025
- Parameters
- N/A
- Context window
- 1M
- Max output
- 1M
- Inputs
- audio, image, text, video
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Gemini 3.1 Flash Lite 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 3.1 Flash-Lite | Released | LLMBoard50.32 | ParametersN/A | Context1M | Max output1M | Open weightsNo | LicenseProprietary |
Models similar to Gemini 3.1 Flash Lite
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemma 4 26B A4B
GOGoogle
Gemini 2.5 Pro
GOGoogle
Gemini 3.5 Flash Lite
GOGoogle
Gemma 4 31B
GOGoogle
Gemini 3.5 Flash Cyber
GOGoogle
Gemini 3.8 Flash Cyber
What is Gemini 3.1 Flash Lite?
Key information about Gemini 3.1 Flash Lite and its available data.
1 Flash Lite is the first Flash-Lite model in the Gemini 3 series. It accepts text, image, video, audio, and PDF input and has a 1 million-token context window.
Data as of 2026-10-22.
FAQ
Common questions about Gemini 3.1 Flash Lite.
When was Gemini 3.1 Flash Lite released?
Gemini 3.1 Flash Lite's default version was released on Mar 3, 2026.
How much does Gemini 3.1 Flash Lite cost?
Gemini 3.1 Flash Lite's official API price is $0.25 per million input tokens and $1.5 per million output tokens via Google. The lowest tracked third-party offer starts at $0.125 input and $0.75 output via Kilo Gateway.
Who created Gemini 3.1 Flash Lite?
Gemini 3.1 Flash Lite was created by Google.
What is the context window for Gemini 3.1 Flash Lite?
The default version has a 1M token context window.
Is Gemini 3.1 Flash Lite open weight?
No. The default version is not marked as having publicly available weights.