TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

benchmarks evals

Passing Once Collapsed to 25 Percent Across Twenty Runs

Thinkingbox evaluates terminal backend state, policy compliance and collateral effects across 507 business workflows.

Published Updated Story ID: mp-2026-08-23-007
Read the complete editionStory JSON

Summary

Thinkingbox evaluates terminal backend state, policy compliance and collateral effects across 507 business workflows.

The strongest tested model reached 65.36 percent pass-at-one but only 25.25 percent success across twenty attempts on the new benchmark. Many failed runs terminated cleanly after valid state-changing actions, supporting the authors’ argument that a plausible response or tool call is not evidence that the right persistent state transition occurred without extra effects.

Why it matters

Thinkingbox evaluates terminal backend state, policy compliance and collateral effects across 507 business workflows.

Limits and context

  • The strongest tested model reached 65.36 percent pass-at-one but only 25.25 percent success across twenty attempts on the new benchmark.
  • Many failed runs terminated cleanly after valid state-changing actions, supporting the authors’ argument that a plausible response or tool call is not evidence that the right persistent state transition occurred without extra effects.

Key claims

  1. Thinkingbox evaluates terminal backend state, policy compliance and collateral effects across 507 business workflows.

    Qualification: The strongest tested model reached 65.36 percent pass-at-one but only 25.25 percent success across twenty attempts on the new benchmark.

    Evidence: source-2026-08-23-007

Sources

  1. arXiv preprint 2608.19741arXiv · primary research

Corrections

No corrections have been recorded for this story.