Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

MAI-Thinking-1

Score basis

MAI-Thinking-1 is behind the leaders in instruction following, coding, and reasoning. Too few results yet to rate agentic tasks, safety, long context, math, multimodal tasks, multilingual tasks, or factuality.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Limited3 capabilities
  1. Instruction Following−30.8%2 of 3
  2. Coding−36.5%3 of 10
  3. Reasoning−43.3%1 of 6
Not rated7 capabilities

Too few results yet to rate Agentic, Safety, Long Context, Math, Multimodal, Multilingual or Factuality.

Price

No current price is tracked for this model. See the rate card

Evidence

21results on21benchmarks

  • 21 vendor-reported

From 2 sources · latest Oct 7, 2026 · How verification works

MAI-Thinking-1 benchmark results

21 results on 21 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Instruction Following

LimitedFull instruction following ranking

30.8% behind the leader2 of 3 ranked benchmarks measured

Coding

LimitedFull coding ranking

36.5% behind the leader3 of 10 ranked benchmarks measured

Reasoning

LimitedFull reasoning ranking

43.3% behind the leader1 of 6 ranked benchmarks measured

Long Context

Not enough dataFull long context ranking

0 of 3 ranked benchmarks measured

Math

Not enough dataFull math ranking

0 of 5 ranked benchmarks measured

Factuality

Not enough dataFull factuality ranking

0 of 4 ranked benchmarks measured

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 5 more resultsHide 5 results

MAI-Thinking-1: common questions

Who makes MAI-Thinking-1?

MAI-Thinking-1 is made by Microsoft.

What is MAI-Thinking-1 good at?

MAI-Thinking-1 is behind the leaders in instruction following, coding, and reasoning. Too few results yet to rate agentic tasks, safety, long context, math, multimodal tasks, multilingual tasks, or factuality.

How many benchmarks has MAI-Thinking-1 been tested on?

We track 21 results for MAI-Thinking-1 on 21 benchmarks from 2 sources. The latest was recorded on Oct 7, 2026.

About this record

Where MAI-Thinking-1's numbers come from, and every name it appears under.

Tracked since
Jun 3, 2026
Newest source mention
Jun 3, 2026

Where the results come from

Verification: 21 scores · 0 independently verified · 21 vendor-reported. How these tiers are assigned

From 2 sources on 2 sites. api.llm-stats.com supplies 17 of them. Bars are coloured by trust tier.

  • api.llm-stats.com17
  • microsoft.ai4