modelgrep
M

Microsoft models

3models tracked · ranked by intelligence, speed & price

Quick answer · Updated June 2026

Microsoft's smartest model is Phi 4 (10.4 on the Intelligence Index), its fastest is Phi 4 Mini Instruct at 276 tokens/sec, and its cheapest is Phi 4 at $0.065 per million input tokens. All 3 Microsoft models are compared below by intelligence, speed, latency, context and price.

Smartest
10.4
microsoft/phi-4
Fastest
276 t/s
microsoft/phi-4-mini-instruct
Cheapest
$0.065/M
microsoft/phi-4
ModelIntelIn $/MContext
phi-4
JSON
10.4$0.06516K
phi-4-mini-instruct
JSON
8.4$0.080131K
wizardlm-2-8x22b
JSON
$0.62066K