Google model product
Gemini 2.5 Flash Lite
5 Flash Lite is a Google DeepMind model for reasoning, science, mathematics, code generation, and other tasks.
Updated Sep 8, 2026. Default version: Gemini 2.5 Flash-Lite
LLMBoard Score19.3Gemini 2.5 Flash-Lite
Coverage40%12 benchmark families
Context window1MTokens
Official input price$0.10Google API
Gemini 2.5 Flash Lite Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemini 2.5 Flash Lite Benchmark Results
Benchmark scores for Gemini 2.5 Flash-Lite.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkArc | Score2.50% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkFACTS Grounding | Score84.10% | Rank03 | Participants13 | Percentile83.33% | EvidenceC | Evaluated |
| BenchmarkMRCR v2 | Score16.60% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkGlobal-MMLU-Lite | Score81.10% | Rank05 | Participants15 | Percentile71.43% | EvidenceC | Evaluated |
| BenchmarkVibe-Eval | Score51.30% | Rank06 | Participants8 | Percentile28.57% | EvidenceC | Evaluated |
| BenchmarkAider-Polyglot | Score26.70% | Rank21 | Participants22 | Percentile4.76% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score72.90% | Rank27 | Participants64 | Percentile58.73% | EvidenceC | Evaluated |
| BenchmarkSimpleQA | Score10.70% | Rank40 | Participants47 | Percentile15.22% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score33.70% | Rank60 | Participants75 | Percentile20.27% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision | Score1,187.27 rating | Rank69 | Participants107 | Percentile35.85% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,187.88 rating | Rank69 | Participants107 | Percentile35.85% | EvidenceA | Evaluated |
| BenchmarkHumanity's Last Exam | Score5.10% | Rank100 | Participants103 | Percentile2.94% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score49.80% | Rank106 | Participants119 | Percentile11.02% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score31.60% | Rank109 | Participants113 | Percentile3.57% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text | Score1,368.92 rating | Rank123 | Participants210 | Percentile41.63% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,374.50 rating | Rank128 | Participants210 | Percentile39.23% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score64.60% | Rank163 | Participants247 | Percentile34.15% | EvidenceC | Evaluated |
Gemini 2.5 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 style control | Categorycaptioning | Rank18 | Rating / score1,185.93 | Votes387 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing | Rank19 | Rating / score1,188.35 | Votes1,311 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing | Rank20 | Rating / score1,188.35 | Votes1,311 | ObservationsN/A | Result date |
| Arenavision | Categorycaptioning | Rank22 | Rating / score1,186.15 | Votes387 | ObservationsN/A | Result date |
| Arenavision style control | Categoryentity recognition | Rank31 | Rating / score1,183.60 | Votes414 | ObservationsN/A | Result date |
| Arenavision | Categoryentity recognition | Rank34 | Rating / score1,186.05 | Votes414 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank54 | Rating / score1,189.06 | Votes1,387 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank58 | Rating / score1,186.92 | Votes1,387 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank58 | Rating / score1,181.72 | Votes1,188 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank63 | Rating / score1,192.64 | Votes1,663 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank64 | Rating / score1,180.81 | Votes1,188 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank64 | Rating / score1,196.11 | Votes1,663 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank66 | Rating / score1,190.29 | Votes1,330 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank67 | Rating / score1,185.68 | Votes2,446 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank67 | Rating / score1,190.52 | Votes16,600 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank67 | Rating / score1,192.70 | Votes1,330 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank68 | Rating / score1,188.03 | Votes10,516 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank68 | Rating / score1,192.67 | Votes16,600 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank69 | Rating / score1,187.27 | Votes35,977 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank69 | Rating / score1,188.91 | Votes10,516 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank69 | Rating / score1,187.88 | Votes35,977 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank70 | Rating / score1,186.63 | Votes2,446 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank81 | Rating / score1,363.20 | Votes725 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank84 | Rating / score1,358.25 | Votes725 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank85 | Rating / score1,348.24 | Votes796 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank88 | Rating / score1,353.83 | Votes796 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank99 | Rating / score1,366.03 | Votes4,126 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank101 | Rating / score1,374.21 | Votes7,028 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank103 | Rating / score1,373.23 | Votes841 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank103 | Rating / score1,371.40 | Votes4,126 | ObservationsN/A | Result date |
Gemini 2.5 Flash Lite Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.10 input, $0.40 output per 1M
- Official provider
- Lowest third-party
- From $0.07 input, $0.28 output per 1M via Poe
- Tracked offerings
- 22
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderKenari | Provider model IDgemini-2-5-flash-lite | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderPoe | Provider model IDgoogle/gemini-2.5-flash-lite | Regionglobal | Input / 1M$0.07 | Output / 1M$0.28 | Context1M | Updated |
| ProviderJiekou.AI | Provider model IDgemini-2.5-flash-lite | Regionglobal | Input / 1M$0.09 | Output / 1M$0.36 | Context1M | Updated |
| ProviderOrcaRouter | Provider model IDgoogle/gemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDgemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context1M | Updated |
| ProviderVertex | Provider model IDgemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context1M | Updated |
| ProviderGoogle | Provider model IDgemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context1M | Updated |
| ProviderImpossibl | Provider model IDgoogle/gemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDgoogle/gemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context1M | Updated |
| ProviderCrossModel | Provider model IDgemini/gemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context1M | Updated |
| ProviderNEAR AI Cloud | Provider model IDgoogle/gemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context1M | Updated |
| ProviderLLMTR | Provider model IDgoogle/gemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.10 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDgoogle/gemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context1M | Updated |
| ProviderZenMux | Provider model IDgoogle/gemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context1M | Updated |
| ProviderSAP AI Core | Provider model IDgemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context1M | Updated |
| ProviderOfox | Provider model IDgoogle/gemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context1M | Updated |
| ProviderHelicone | Provider model IDgemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDgoogle/gemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDgemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDgoogle/gemini-2.5-flash-lite | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context1M | Updated |
Gemini 2.5 Flash Lite Runtime Performance
Provider-specific output speed and catalog latency for Gemini 2.5 Flash-Lite. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderGoogle | Output Speed5.69 tok/s | Catalog Latency0.44 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 2.5 Flash Lite Specifications
Technical details for the model's default version.
- Version
- Gemini 2.5 Flash-Lite
- Released
- Jun 17, 2025
- Knowledge cutoff
- Jan 1, 2025
- Parameters
- N/A
- Context window
- 1M
- Max output
- 65.5K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Creative Commons Attribution 4.0 License
Gemini 2.5 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 2.5 Flash-Lite | Released | LLMBoard19.26 | ParametersN/A | Context1M | Max output65.5K | Open weightsNo | LicenseCreative Commons Attribution 4.0 License |
Models similar to Gemini 2.5 Flash Lite
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemini 1.5 Pro
GOGoogle
Gemini 2.0 Flash Lite
GOGoogle
Gemma 4 E4B
GOGoogle
Gemma 3 27B
GOGoogle
Gemini 2.0 Flash
GOGoogle
Gemini 1.5 Flash
What is Gemini 2.5 Flash Lite?
Key information about Gemini 2.5 Flash Lite and its available data.
5 Flash Lite is a Google DeepMind model optimized for low-latency use cases, with multilingual performance, long context understanding, multimodal input, and a 1 million-token context length.
Data as of 2026-09-08.
FAQ
Common questions about Gemini 2.5 Flash Lite.
When was Gemini 2.5 Flash Lite released?
Gemini 2.5 Flash Lite's default version was released on Jun 17, 2025.
How much does Gemini 2.5 Flash Lite cost?
Gemini 2.5 Flash Lite's official API price is $0.10 per million input tokens and $0.40 per million output tokens via Google. The lowest tracked third-party offer starts at $0.07 input and $0.28 output via Poe.
Who created Gemini 2.5 Flash Lite?
Gemini 2.5 Flash Lite was created by Google.
What is the context window for Gemini 2.5 Flash Lite?
The default version has a 1M token context window.
Is Gemini 2.5 Flash Lite open weight?
No. The default version is not marked as having publicly available weights.