Microsoft model product
Phi 3.5 MoE
6B active) and a 128K context window.
Updated Aug 17, 2026. Default version: Phi-3.5-MoE-instruct
LLMBoard Score4.4Phi-3.5-MoE-instruct
Coverage100%21 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Phi 3.5 MoE Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Phi 3.5 MoE Benchmark Results
Benchmark scores for Phi-3.5-MoE-instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkGovReport | Score26.4% | Rank01 | Participants2 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkMEGA MLQA | Score65.3% | Rank01 | Participants2 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkMEGA TyDi QA | Score67.1% | Rank01 | Participants2 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkMEGA UDPOS | Score60.4% | Rank01 | Participants2 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkMEGA XCOPA | Score76.6% | Rank01 | Participants2 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkMEGA XStoryCloze | Score82.8% | Rank01 | Participants2 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkOpenBookQA | Score89.6% | Rank01 | Participants5 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkPIQA | Score88.6% | Rank01 | Participants11 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkRepoQA | Score85.0% | Rank01 | Participants2 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkSocial IQa | Score78.0% | Rank01 | Participants9 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkSummScreenFD | Score16.9% | Rank01 | Participants2 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkQasper | Score40.0% | Rank02 | Participants2 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkQMSum | Score19.9% | Rank02 | Participants2 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkSQuALITY | Score24.1% | Rank02 | Participants5 | Percentile75.0% | EvidenceC | Evaluated |
| BenchmarkTruthfulQA | Score77.5% | Rank02 | Participants18 | Percentile94.1% | EvidenceC | Evaluated |
| BenchmarkBoolQ | Score84.6% | Rank03 | Participants10 | Percentile77.8% | EvidenceC | Evaluated |
| BenchmarkRULER | Score87.1% | Rank03 | Participants4 | Percentile33.3% | EvidenceC | Evaluated |
| BenchmarkBIG-Bench Hard | Score79.1% | Rank09 | Participants21 | Percentile60.0% | EvidenceC | Evaluated |
| BenchmarkWinogrande | Score81.3% | Rank09 | Participants22 | Percentile61.9% | EvidenceC | Evaluated |
| BenchmarkARC-C | Score91.0% | Rank10 | Participants34 | Percentile72.7% | EvidenceC | Evaluated |
| BenchmarkMBPP | Score80.8% | Rank12 | Participants33 | Percentile65.6% | EvidenceC | Evaluated |
| BenchmarkHellaSwag | Score83.8% | Rank14 | Participants27 | Percentile50.0% | EvidenceC | Evaluated |
| BenchmarkArena Hard | Score37.9% | Rank22 | Participants26 | Percentile16.0% | EvidenceC | Evaluated |
| BenchmarkMGSM | Score58.7% | Rank26 | Participants31 | Percentile16.7% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score88.7% | Rank30 | Participants48 | Percentile38.3% | EvidenceC | Evaluated |
| BenchmarkMMMLU | Score69.9% | Rank44 | Participants49 | Percentile10.4% | EvidenceC | Evaluated |
| BenchmarkMATH | Score59.5% | Rank49 | Participants71 | Percentile31.4% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score70.7% | Rank57 | Participants66 | Percentile13.8% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score78.9% | Rank69 | Participants101 | Percentile32.0% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score45.3% | Rank124 | Participants134 | Percentile7.5% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score36.8% | Rank216 | Participants239 | Percentile9.7% | EvidenceC | Evaluated |
Phi 3.5 MoE Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Phi 3.5 MoE 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 MoE Runtime Performance
Provider-specific output speed and catalog latency for Phi-3.5-MoE-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 MoE Specifications
Technical details for the model's default version.
- Version
- Phi-3.5-MoE-instruct
- Released
- Aug 23, 2024
- Knowledge cutoff
- Unknown
- Parameters
- 60B
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- MIT
Phi 3.5 MoE 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-MoE-instruct | Released | LLMBoard4.4 | Parameters60B | ContextN/A | Max outputN/A | Open weightsNo | LicenseMIT |
Phi 3.5 MoE vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Phi 3.5 MoE
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MI
Phi 4 multimodal
Microsoft
MI
Phi 4
Microsoft
MI
Phi 3.5 vision
Microsoft
MI
Phi 3.5 mini
Microsoft
MI
Phi 4 Mini
Microsoft
MI
Phi 4 Mini Reasoning
Microsoft
What is Phi 3.5 MoE?
Key information about Phi 3.5 MoE and its available data.
6B active) and a 128K context window. It excels at reasoning, math, coding, and multilingual tasks, outperforming larger dense models in many benchmarks. It underwent a thorough safety post-training process (SFT + DPO) and is licensed under MIT.
This model is ideal for scenarios where efficiency and high performance are both required, particularly in multi-lingual or reasoning-intensive tasks.
Data as of 2026-08-17.
FAQ
Common questions about Phi 3.5 MoE.
When was Phi 3.5 MoE released?
Phi 3.5 MoE's default version was released on Aug 23, 2024.
How much does Phi 3.5 MoE cost?
No official standard PAYG price is currently available for Phi 3.5 MoE.
Who created Phi 3.5 MoE?
Phi 3.5 MoE was created by Microsoft.
What is the context window for Phi 3.5 MoE?
A context window is not available for the default version.
Is Phi 3.5 MoE open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Phi 3.5 MoE?
No provider offering is currently linked to the default version.
What models should I compare Phi 3.5 MoE with?
Nearby ranked alternatives include Phi 4 multimodal, Qwen2.5 7B, Qwen2.5 Coder 32B.