Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Microsoft AI models

18 MODELS TRACKED

18 published Microsoft models are tracked, with Mage-VL-4B carrying the deepest benchmark surface (46 results). Every score is source-attributed with a verification tier; every model opens its full dossier.

● LIVE ROSTER18 MODELSDATA AS OF October 1, 2026 UTCREFRESHES WITH THE PIPELINE

The rosterRANKED BY BENCHMARK SURFACE

#ModelBenchmarksStatusInput priceLast seen
01Mage-VL-4B46UNPRICED—2026-07-26
02Phi 4 R V 15B38UNPRICED—2026-07-26
03Phi 4 Reasoning Plus18UNPRICED—2026-08-23
04Phi 4 Multimodal Instruct58UNPRICED—2026-09-03
05Phi 440CURRENT$0.07/M2026-08-23
06Phi 3.5 MoE Instruct18UNPRICED—2026-08-29
07Phi 3.5 Mini Instruct18UNPRICED—2026-08-29
08Phi 3.5 Vision Instruct66UNPRICED—2026-09-17
09Phi 3 Medium 128K Instruct0UNPRICED—2026-05-18
10Phi 3 Medium 4K Instruct13UNPRICED—2026-09-21
11Phi 3 Small 128K Instruct0UNPRICED—2026-05-18
12Phi 3 Small 8K Instruct5UNPRICED—2026-07-02
13Phi 3 Mini 4K Instruct41UNPRICED—2026-08-29
14Phi 3 Mini 128K Instruct0UNPRICED—2026-05-18
15Phi 4 Mini Instruct43LEGACY—2026-08-29
16Phi 26UNPRICED—2026-07-02
17MAI-Code-1-Flash10CURRENT—2026-09-09
18MAI-Thinking-131CURRENT—2026-10-01

Benchmark counts are source-attributed default-configuration results; input price is the cheapest current per-Mtok rate across tracked providers. Open a model for its full surface.