Skip to content
Vareon
Start a pilot
en

A steady reading cost, however long the history.

LongMemEval asks questions about long chat histories between a person and an assistant. As the history grew to forty sessions, the reading behind each of Duplex’s answers levelled off, and where a fact had changed, it answered with the current one.

LongMemEval, by Wu et al., ICLR 2025. The benchmark →

See it happen →Every result

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

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

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

The history doubles. The reading levels off.

As sessions pile up, the whole history doubles with them.*

Step 1 of 4: The history

3.7× less reading for every answer.*

At forty sessions of history, against sending the whole history to the model.

Step 1 of 3: Reading

Duplex sent 24,176 tokens a question. Sending the whole history meant 88,798.*

It answers with the fact as it stands now.

Where a fact changed partway through the history, Duplex gave the current answer 96% of the time.*

  • Temporal reasoning: 90% correct.*
  • Reasoning across several sessions: 89% correct.*
Step 1 of 4: Stated

Early in the history, a fact is stated: the team uses vendor A.*

How it was run.

Benchmark
LongMemEval, by Wu et al. (ICLR 2025), from the cleaned public release.
The work
Answer a question about a long chat history between a person and an assistant.
Histories
The sessions holding the answer, mixed with unrelated sessions from a pool of 19,195, at 2, 5, 10, 20 and 40 sessions.
Scale
50 questions at five history sizes: 250 answers for every approach.
Models
GPT-5.5 read what each approach supplied and wrote every answer; a separate model judged them.

What it means for your work.

  • Long-running work stays affordable.

    From twenty to forty sessions the history doubled, and the cost of each answer stayed at $0.032.*

  • Answers follow what changed.

    Where a fact had changed, Duplex answered with the current one 96% of the time.*

  • It answers, rather than holding back.

    Duplex declined 5 of the 250 questions, and answered the rest.*

Brings the right history to each step →
Next: Blocks every attack, and lets ordinary work through.Read it →

See it on your own work.

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

Start a pilot →Every result

Your data, your choice.

vareon.com uses no analytics, advertising or third-party trackers, and Vareon does not sell your data. If you accept, the site remembers your light or dark appearance on this device for a year. If you deny, it stores only what it needs to work.

You can change your choice at any time under Privacy choices at the foot of every page. Read the privacy policy