Google model product
MedGemma 4B IT is a multimodal Gemma 3 variant trained for medical text and image comprehension.
Updated Sep 8, 2026. Default version: MedGemma 4B IT
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for MedGemma 4B IT.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkCheXpert CXR | Score48.10% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkDermMCQA | Score71.80% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMIMIC CXR | Score88.90% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkPathMCQA | Score69.80% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkVQA-Rad | Score49.90% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSlakeVQA | Score62.30% | Rank04 | Participants4 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMedXpertQA | Score18.80% | Rank12 | Participants12 | Percentile0.00% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
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 MedGemma 4B IT. Runtime does not affect the capability score.
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.
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 |
|---|
| VersionMedGemma 4B IT | Released | LLMBoard0.00 | Parameters4.3B | ContextN/A | Max outputN/A | Open weightsYes | LicenseHealth AI Developer Foundations terms of use |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about MedGemma 4B IT and its available data.
MedGemma 4B IT is a medical multimodal model from Google that uses a SigLIP image encoder and an LLM trained on diverse medical data. It is primarily evaluated on single-image tasks and has not been evaluated for multi-turn applications.
Data as of 2026-09-08.
Common questions about MedGemma 4B IT.
MedGemma 4B IT's default version was released on May 20, 2025.
No official standard PAYG price is currently available for MedGemma 4B IT.
MedGemma 4B IT was created by Google.
A context window is not available for the default version.
Yes. The default version is marked as open weight under Health AI Developer Foundations terms of use.
No provider offering is currently linked to the default version.