Microsoft model product
Phi 3.5 vision
2B-parameter open multimodal model with up to 128K context tokens.
Updated Aug 17, 2026. Default version: Phi-3.5-vision-instruct
LLMBoard Score0.0Phi-3.5-vision-instruct
Coverage20%7 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Phi 3.5 vision Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Phi 3.5 vision Benchmark Results
Benchmark scores for Phi-3.5-vision-instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkScienceQA | Score91.3% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkInterGPS | Score36.3% | Rank02 | Participants2 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkPOPE | Score86.1% | Rank02 | Participants3 | Percentile50.0% | EvidenceC | Evaluated |
| BenchmarkMMBench | Score81.9% | Rank06 | Participants9 | Percentile37.5% | EvidenceC | Evaluated |
| BenchmarkTextVQA | Score72.0% | Rank13 | Participants16 | Percentile20.0% | EvidenceC | Evaluated |
| BenchmarkChartQA | Score81.8% | Rank17 | Participants26 | Percentile36.0% | EvidenceC | Evaluated |
| BenchmarkAI2D | Score78.1% | Rank30 | Participants33 | Percentile9.4% | EvidenceC | Evaluated |
| BenchmarkMathVista | Score43.9% | Rank38 | Participants39 | Percentile2.6% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score43.0% | Rank61 | Participants63 | Percentile3.2% | EvidenceC | Evaluated |
Phi 3.5 vision Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categoryoverall | Rank144 | Rating / score851.6 | Votes2,592 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank144 | Rating / score920.8 | Votes2,592 | ObservationsN/A | Result date |
Phi 3.5 vision 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.
Phi 3.5 vision Runtime Performance
Provider-specific output speed and catalog latency for Phi-3.5-vision-instruct. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo 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.
Phi 3.5 vision Specifications
Technical details for the model's default version.
- Version
- Phi-3.5-vision-instruct
- Released
- Aug 23, 2024
- Knowledge cutoff
- Unknown
- Parameters
- 4.2B
- Context window
- N/A
- Max output
- N/A
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- MIT
Phi 3.5 vision 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 |
|---|
| VersionPhi-3.5-vision-instruct | Released | LLMBoard0.0 | Parameters4.2B | ContextN/A | Max outputN/A | Open weightsNo | LicenseMIT |
Phi 3.5 vision vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Phi 3.5 vision
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MI
Phi 3.5 mini
Microsoft
MI
Phi 4 Mini
Microsoft
MI
Phi 3.5 MoE
Microsoft
MI
Phi 4 multimodal
Microsoft
MI
Phi 4
Microsoft
MI
Phi 4 Mini Reasoning
Microsoft
What is Phi 3.5 vision?
Key information about Phi 3.5 vision and its available data.
2B-parameter open multimodal model with up to 128K context tokens. It emphasizes multi-frame image understanding and reasoning, boosting performance on single-image benchmarks while enabling multi-image comparison, summarization, and even video analysis.
The model underwent safety post-training for improved instruction-following, alignment, and robust handling of visual and text inputs, and is released under the MIT license.
Data as of 2026-08-17.
FAQ
Common questions about Phi 3.5 vision.
When was Phi 3.5 vision released?
Phi 3.5 vision's default version was released on Aug 23, 2024.
How much does Phi 3.5 vision cost?
No official standard PAYG price is currently available for Phi 3.5 vision.
Who created Phi 3.5 vision?
Phi 3.5 vision was created by Microsoft.
What is the context window for Phi 3.5 vision?
A context window is not available for the default version.
Is Phi 3.5 vision open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Phi 3.5 vision?
No provider offering is currently linked to the default version.
What models should I compare Phi 3.5 vision with?
Nearby ranked alternatives include Mistral NeMo, Llama 3.2 3B, North Micro Vision.