Google model product
Gemma 2 9B
Gemma 2 9B is Google's instruction-tuned language model for dialogue applications.
Updated Sep 8, 2026. Default version: Gemma 2 9B
LLMBoard Score0.0Gemma 2 9B
Coverage60%16 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Gemma 2 9B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemma 2 9B Benchmark Results
Benchmark scores for Gemma 2 9B.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkARC-E | Score88.00% | Rank02 | Participants8 | Percentile85.71% | EvidenceC | Evaluated |
| BenchmarkBIG-Bench | Score68.20% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkNatural Questions | Score29.20% | Rank03 | Participants7 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkBoolQ | Score84.20% | Rank04 | Participants10 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkPIQA | Score81.70% | Rank04 | Participants11 | Percentile70.00% | EvidenceC | Evaluated |
| BenchmarkSocial IQa | Score53.40% | Rank05 | Participants9 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkAGIEval | Score52.80% | Rank06 | Participants10 | Percentile44.44% | EvidenceC | Evaluated |
| BenchmarkTriviaQA | Score76.60% | Rank08 | Participants18 | Percentile58.82% | EvidenceC | Evaluated |
| BenchmarkWinogrande | Score80.60% | Rank11 | Participants22 | Percentile52.38% | EvidenceC | Evaluated |
| BenchmarkHellaSwag | Score81.90% | Rank17 | Participants27 | Percentile38.46% | EvidenceC | Evaluated |
| BenchmarkARC-C | Score68.40% | Rank25 | Participants34 | Percentile27.27% | EvidenceC | Evaluated |
| BenchmarkMBPP | Score52.40% | Rank32 | Participants33 | Percentile3.13% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score68.60% | Rank45 | Participants48 | Percentile6.38% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score40.20% | Rank65 | Participants66 | Percentile1.54% | EvidenceC | Evaluated |
| BenchmarkMATH | Score36.60% | Rank68 | Participants71 | Percentile4.29% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score71.30% | Rank80 | Participants101 | Percentile21.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,279.98 rating | Rank190 | Participants210 | Percentile9.57% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,226.84 rating | Rank192 | Participants210 | Percentile8.61% | EvidenceA | Evaluated |
Gemma 2 9B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext style control | Categoryjapanese | Rank156 | Rating / score1,195.12 | Votes1,301 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank159 | Rating / score1,144.29 | Votes1,301 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank161 | Rating / score1,268.95 | Votes318 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank163 | Rating / score1,202.44 | Votes1,087 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank164 | Rating / score1,218.19 | Votes318 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank166 | Rating / score1,136.38 | Votes1,087 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank168 | Rating / score1,267.43 | Votes614 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank171 | Rating / score1,199.50 | Votes614 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank171 | Rating / score1,259.15 | Votes591 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank172 | Rating / score1,189.69 | Votes591 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank172 | Rating / score1,283.33 | Votes1,671 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank175 | Rating / score1,326.65 | Votes543 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank178 | Rating / score1,268.46 | Votes543 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank179 | Rating / score1,225.01 | Votes753 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank179 | Rating / score1,289.94 | Votes753 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank180 | Rating / score1,267.97 | Votes1,692 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank181 | Rating / score1,238.60 | Votes1,671 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank182 | Rating / score1,299.86 | Votes516 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank184 | Rating / score1,273.96 | Votes2,801 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank185 | Rating / score1,220.95 | Votes516 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank185 | Rating / score1,271.46 | Votes1,119 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank186 | Rating / score1,221.88 | Votes1,121 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank186 | Rating / score1,284.09 | Votes1,121 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank187 | Rating / score1,214.55 | Votes1,692 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank187 | Rating / score1,288.60 | Votes841 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank188 | Rating / score1,271.63 | Votes1,660 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank189 | Rating / score1,296.67 | Votes5,834 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank189 | Rating / score1,255.21 | Votes4,238 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank190 | Rating / score1,225.52 | Votes2,801 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexclude ties | Rank190 | Rating / score1,195.75 | Votes6,321 | ObservationsN/A | Result date |
Gemma 2 9B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
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.
Gemma 2 9B Runtime Performance
Provider-specific output speed and catalog latency for Gemma 2 9B. 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.
Gemma 2 9B Specifications
Technical details for the model's default version.
- Version
- Gemma 2 9B
- Released
- Jun 27, 2024
- Knowledge cutoff
- Unknown
- Parameters
- 9.2B
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- Gemma
Gemma 2 9B 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 |
|---|
| VersionGemma 2 9B | Released | LLMBoard0.00 | Parameters9.2B | ContextN/A | Max outputN/A | Open weightsYes | LicenseGemma |
Models similar to Gemma 2 9B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
MedGemma 4B IT
GOGoogle
Gemini 1.0 Pro
GOGoogle
Gemini 1.5 Flash 8B
GOGoogle
Gemma 2 27B
GOGoogle
Gemma 3 1B
GOGoogle
Gemma 3 4B
What is Gemma 2 9B?
Key information about Gemma 2 9B and its available data.
Gemma 2 9B IT is an instruction-tuned version of Google's Gemma 2 9B base model, trained on 8 trillion tokens of web data, code, and math content. It uses sliding window attention, logit soft-capping, knowledge distillation, supervised fine-tuning, RLHF, and model merging using WARP.
Data as of 2026-09-08.
FAQ
Common questions about Gemma 2 9B.
When was Gemma 2 9B released?
Gemma 2 9B's default version was released on Jun 27, 2024.
How much does Gemma 2 9B cost?
No official standard PAYG price is currently available for Gemma 2 9B.
Who created Gemma 2 9B?
Gemma 2 9B was created by Google.
What is the context window for Gemma 2 9B?
A context window is not available for the default version.
Is Gemma 2 9B open weight?
Yes. The default version is marked as open weight under Gemma.
How many API providers offer Gemma 2 9B?
No provider offering is currently linked to the default version.