What Duplex delivers, in numbers.

• −90.3%*Model calls, with accuracy up94.6% accurate, against 59.8% for the model alone
• 0%*Stale answers after a rule changeCache and retrieval: 72%
• 6 / 6*Tests where Duplex beat fine-tuning+30.3 points on average, with no training run
• 3 / 3*Frontier models beaten at predicting system changesOn a public enterprise benchmark, with no model calls

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

• 90% fewer model calls, and more accurate.*

  94.6%*Accuracy, the highest in the testThe model alone 59.8% · with a cache 77.3%
  • −90.3% Model calls · −84.8% cost · −81.9% latency*
  • ~23× Faster once learned · ≈97 ms against ≈2,231 ms*

  A 3,000-decision stream in which the rules changed five times, against the frontier model alone and with a semantic cache; a 300-decision run added a cache with retrieval and a knowledge graph. Every approach used the same model.

  See the full result →Learns and unlearns →

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

  94.1 to 94.8%*Duplex accuracy, at every one of eight settingsThe best a cache reached: 77.3%
  • 84 to 91% On three fresh runs of 1,000 decisions · The best a cache reached: about 73%*

  A 3,000-decision stream with every approach swept across its full range of settings, then three fresh runs of 1,000 decisions in a second, independent setup.

  See the full result →Decides whether to answer, hand over or decline →

• Keeps learning without forgetting, going stale or growing.

  5 / 5*Requirements for learning in production, all met on every runCache and retrieval averaged 2.2 / 5 · online fine-tuning 4 / 5
  • 0% Stale answers after a policy change · Cache and retrieval 72%*
  • Fixed Footprint over time · Cache and retrieval grew to ≈1,300 rows*

  Ten runs, with the same supervision and the same inputs for every approach.

  See the full result →Stays fast and sound as it grows →

• Handles new wording, and spots the look-alikes.

  7.5%*Wrong answers on look-alike requestsA cache 45.3%, about 6× more
  • 98.98% Of requests handled correctly: answered right, or handed to your AI · Duplex answered 95.78% of known requests itself*
  • 0.996 Score for telling familiar from new, out of 1 · A cache 0.930*

  Ten learned intents and six levels of novelty, from exact repeats to requests from another domain, over ten runs.

  See the full result →Handles cases it has never seen →

• Plans the shortest route, with zero model tokens.

  100%*Plan success, on every runA reactive agent: 0% · Duplex used no model tokens
  • 0% A reactive greedy agent*
  • ~204 Tokens per decision a frontier model spends to match it*

  A multi-step world over ten runs, against a reactive agent and a frontier model given the same task.

  See the full result →Sees what an action will do →

• Keeps agent tasks succeeding, with fewer model calls.

  83.3%*Task successThe model on every turn: 82.5%
  • 12.8% Turns completed without the model · ≈15% fewer model calls*
  • 100% Success on new tasks*

  Τ-bench (tau2-bench), retail, by Sierra Research. The unmodified retail environment, with the same model, tools and user simulator for every approach, over three runs of forty episodes.

  See the full result →Runs model and tool calls under your rules →

• A steady reading cost, however long the history.

  96%*Current answers where a fact had changedThe new fact, not the old one
  • 3.7× Less reading per question than reading the whole history · At forty sessions of history*
  • 84% Accuracy at forty sessions of history*

  LongMemEval, by Wu et al., ICLR 2025. Fifty questions, each asked with the history at 2, 5, 10, 20 and 40 sessions.

  See the full result →Brings the right history to each step →

• Blocks every attack, and lets ordinary work through.

  0%*Attack successAcross six families of paraphrased attacks
  • 0.7% False refusals · The lowest of any approach that blocked every attack*
  • 40 / 40 Poisoned samples removed · Accuracy back within 1 point*

  Six attack families, paraphrased, with harmless requests written to resemble the attacks.

  See the full result →Your rules come first →

• Learns a new skill on its own, with the model switched off.

  100%*Tasks completed with the model off, on every runA frontier model needed ≈507 calls per run
  • 0.26 ms To reuse a skill · At 0 model calls*
  • 627 Unsafe actions refused per run · And the safe skill was still learned*

  Four suites over ten runs, each scored by its worst run.

  See the full result →Learns new skills on its own →

• Beat three frontier models at predicting system changes.

  0.256*System-change prediction scoreGPT-5.1 0.166 · Gemini 3 Pro 0.205 · Claude Sonnet 4.5 0.204
  • $0 Model spend · 570 predictions at zero calls; 84 on a frontier model cost $13.40*
  • ~80% Decisions answered from what it learned · Your AI took the rest*

  World of Workflows, by Skyfall Research / ServiceNow. Three offline tracks, scored by the benchmark authors’ own evaluator, over three runs.

  See the full result →Sees what an action will do →

• Beats fine-tuning, with no training run.

  6 / 6*Tests where Duplex beat a fine-tuned adapter+30.3 points on average
  • 0 Retraining to move to another model family · The adapters moved in 0 of 6*
  • 60 to 79% Answered from what it learned · On either model family*

  Three public intent datasets, two open model families and three runs, with the same frozen model and data for every approach.

  See the full result →Adapts your model without retraining →