Model vendor
Technology company
Updated Aug 11, 2026. Data as of 2026-08-11
Default-version specifications and scored-version capability values are labeled separately.
| MI | MAI-Thinking-1 | 55.1 | 100.0% | N/A | Closed weights | MAI-Thinking-1 | |
| MI | MAI-Code-1-Flash | 50.4 | 100.0% | 256K | Closed weights | MAI-Code-1-Flash | |
| MI | Phi 4 Reasoning Plus | 26.8 | 100.0% | N/A | Closed weights | Phi 4 Reasoning Plus | |
| MI | Phi 4 Reasoning | 22.0 | 100.0% | N/A | Closed weights | Phi 4 Reasoning | |
| MI | Phi 4 Mini Reasoning | 13.8 | 40.0% | N/A | Closed weights | Phi 4 Mini Reasoning | |
| MI | Phi 4 | 9.4 | 100.0% | 16K | Closed weights | Phi 4 | |
| MI | Phi-4-multimodal-instruct | 7.4 | 0.0% | 128K | Closed weights | Phi-4-multimodal-instruct | |
| MI | Phi-3.5-MoE-instruct | 4.9 | 100.0% | N/A | Closed weights | Phi-3.5-MoE-instruct | |
| MI | Phi-3.5-mini-instruct | 0.0 | 100.0% | 128K | Closed weights | Phi-3.5-mini-instruct | |
| MI | Phi-3.5-vision-instruct | 0.0 | 0.0% | N/A | Closed weights | Phi-3.5-vision-instruct | |
| MI | Phi 4 Mini | 0.0 | 60.0% | 128K | Open weights | Phi 4 Mini | |
| MI | MAI-Image-2.5 | N/A | N/A | N/A | Closed weights | N/A | Not scored |
Each unique model uses its latest scored version.
Leading Microsoft models by score, price and context window.
Background and model catalog information for Microsoft.
Technology company
Model ownership is separate from API hosting. One model can be offered by multiple API providers with different prices.
Catalog data as of 2026-08-11.
Common questions about Microsoft.
MAI Thinking 1 currently has the strongest LLMBoard score from this vendor.
The catalog contains 12 independently selectable Microsoft models and 12 versions.
Not necessarily. Vendor identifies the model developer; API providers are tracked separately.
1 current default versions are marked as open weight.