Google model product
5 Flash 8B is a Google multimodal model with 8B parameters, optimized for fast inference.
Updated Sep 8, 2026. Default version: Gemini 1.5 Flash 8B
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Gemini 1.5 Flash 8B.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkWMT23 | Score72.60% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkXSTest | Score92.60% | Rank04 | Participants4 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMRCR | Score54.70% | Rank05 | Participants7 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkFLEURS | Score86.40% | Rank06 | Participants6 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkNatural2Code | Score75.50% | Rank06 | Participants8 | Percentile28.57% | EvidenceC | Evaluated |
| BenchmarkVibe-Eval | Score40.90% | Rank08 | Participants8 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkHiddenMath | Score32.80% | Rank10 | Participants13 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkVideo-MME | Score66.20% | Rank16 | Participants17 | Percentile6.25% | EvidenceC | Evaluated |
| BenchmarkMathVista | Score54.70% | Rank32 | Participants39 | Percentile18.42% | EvidenceC | Evaluated |
| BenchmarkMATH | Score58.70% | Rank50 | Participants71 | Percentile30.00% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score53.70% | Rank54 | Participants64 | Percentile15.87% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision | Score1,044.09 rating | Rank97 | Participants107 | Percentile9.43% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,071.40 rating | Rank97 | Participants107 | Percentile9.43% | EvidenceA | Evaluated |
| BenchmarkMMLU-Pro | Score58.70% | Rank113 | Participants138 | Percentile18.25% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text | Score1,225.63 rating | Rank193 | Participants210 | Percentile8.13% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,258.46 rating | Rank198 | Participants210 | Percentile5.74% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score38.40% | Rank221 | Participants247 | Percentile10.57% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categorychinese | Rank88 | Rating / score972.62 | Votes332 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank88 | Rating / score1,017.71 | Votes332 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank96 | Rating / score1,070.05 | Votes3,348 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank96 | Rating / score1,087.23 | Votes3,348 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank97 | Rating / score1,044.09 | Votes6,243 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank97 | Rating / score1,071.40 | Votes6,243 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank157 | Rating / score1,150.08 | Votes691 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank164 | Rating / score1,139.73 | Votes500 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank165 | Rating / score1,170.56 | Votes691 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank166 | Rating / score1,233.57 | Votes331 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank167 | Rating / score1,205.73 | Votes798 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank168 | Rating / score1,274.46 | Votes331 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank169 | Rating / score1,211.54 | Votes323 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank170 | Rating / score1,164.25 | Votes500 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank172 | Rating / score1,248.39 | Votes323 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank173 | Rating / score1,228.76 | Votes798 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank176 | Rating / score1,230.77 | Votes2,914 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank184 | Rating / score1,234.96 | Votes5,317 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank185 | Rating / score1,225.67 | Votes4,171 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank187 | Rating / score1,247.57 | Votes2,128 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank187 | Rating / score1,213.07 | Votes1,813 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank187 | Rating / score1,271.15 | Votes2,914 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank187 | Rating / score1,253.37 | Votes4,171 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank188 | Rating / score1,217.32 | Votes5,031 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank188 | Rating / score1,206.64 | Votes5,036 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank188 | Rating / score1,214.25 | Votes17,091 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank189 | Rating / score1,226.39 | Votes9,499 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank189 | Rating / score1,237.09 | Votes5,031 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank189 | Rating / score1,229.59 | Votes5,036 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank190 | Rating / score1,185.16 | Votes2,111 | ObservationsN/A | Result date |
Official vendor API pricing appears first, followed by individual provider offers.
The default version has no current input or output token prices.
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 1.5 Flash 8B. Runtime does not affect the capability score.
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderGoogle | Output Speed150.00 tok/s | Catalog Latency0.30 s | Max Input1M | Max Output8.2K | 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 1.5 Flash 8B | Released | LLMBoard0.00 | Parameters8B | Context1M | Max output8.2K | Open weightsNo | LicenseProprietary |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about Gemini 1.5 Flash 8B and its available data.
5 Flash 8B is a Google multimodal large language model that processes audio, images, video, and text. It supports JSON mode, function calling, code execution, and system instructions.
Data as of 2026-09-08.
Common questions about Gemini 1.5 Flash 8B.
Gemini 1.5 Flash 8B's default version was released on Mar 15, 2024.
No official standard PAYG price is currently available for Gemini 1.5 Flash 8B.
Gemini 1.5 Flash 8B 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.
No provider offering is currently linked to the default version.