Skip to content
MatterSpace
Start a pilot

MS Duplex — The Agent Operating System powered by Runtime Intelligence. Rent the model. Own the intelligence.

More accurate at every setting, at a seventh of the cost.

At all eight of its settings, MS Duplex was more accurate than a semantic cache at any of its five, or GPT-5.5 alone at its one, on the same 3,000 decisions. Three more runs, on fresh streams, showed the same order.

See it happen →Every result

Internal benchmarks. Every figure on this page comes from tests MatterSpace ran itself and has not been independently verified. Read the disclaimer

  • 94.1 to 94.8%*MS Duplex accuracy, at every one of eight settingsThe best a cache reached: 77.3%
    MS Duplex accuracy, at every one of eight settings
    MS Duplex94.1 to 94.8%
    The best a cache reached77.3%
  • 84 to 91%*On three fresh runs of 1,000 decisionsThe best a cache reached: about 73%
    On three fresh runs of 1,000 decisions
    MS Duplex84 to 91%
    The best a cache reached≈73%

* Figures from MatterSpace’s internal benchmarks, not independently verified. Read the disclaimer

Every setting, on one chart.

GPT-5.5 alone has one setting: 59.8% accurate, at $0.82 per 1,000 decisions.*

Step 1 of 4: The model

MS Duplex at its worst beats a cache at its best.

The least accurate MS Duplex setting against the most accurate cache setting.

Step 1 of 2: Accuracy

At its least accurate setting, MS Duplex scored 94.1%. The cache, at its most accurate, scored 77.3%.*

Tuning a cache does not buy accuracy.

The same cache, from its loosest matching to its strictest.

Step 1 of 3: Stricter

Tightening a cache’s matching sends more requests to the model: from 4 calls to 212.*

The same order, run after run.

Three fresh runs of 1,000 decisions each, in a second, independent setup.

Step 1 of 2: Accuracy

Over three fresh runs in a second, independent setup, MS Duplex scored 87.7%, and the best cache 73.0%.*

How it was run.

The work
The same customer-operations stream as the cost result: one right action out of about nineteen, or a refusal, with five in-house rule changes.
Settings
MS Duplex at eight settings, from most willing to answer itself to most cautious; a semantic cache at five, from loosest to strictest matching; GPT-5.5 alone at its only one.
Scale
One 3,000-decision stream, then three independent runs of 1,000 decisions in a second setup.
Kept equal
The same recorded GPT-5.5 answers for every point, the same feedback and the same refusal rules.

What it means for your work.

  • Steady at every setting.

    All eight MS Duplex settings landed between 94.1% and 94.8% accurate.*

  • Accuracy a cache cannot reach.

    Across its settings, the cache topped out at 77.3%, and at 44.2% after a rule change.*

  • Cheaper than the model, everywhere.

    Even MS Duplex’s most cautious setting cost less than GPT-5.5 alone, and was 34 points more accurate.*

Decides whether to answer, hand over or decline →
Next: Keeps learning without forgetting, going stale or growing.Read it →

See it on your own work.

From your own assistant to every agent your company runs, a pilot puts MS Duplex on your own work, with the measures agreed before it begins.

Start a pilot →Every result