Measured capability
Browser / Computer Use
Order workflows completed through a real browser with audited state changes.
1 measured exam3 recorded lanesLatest measurement 2026-09-02Published campaign scopeNo category composite
Certified exam
Order desk browser workflow
3 measured model lanes
Model lane
cli/claude-sonnet
10/10100% certified
Lanecli/claude-sonnetDeliveryDelivery not establishedConditionsUnproven
Model failures0Lane errors0Withheld / invalid0 / 0
Elapsed median84.5 seconds · 10/10 observedSteps median18 · 10/10 observedTokens medianNot recordedCost median (USD)Not recorded
delivery equivalence is unproven; delivery is not proved; lane configuration is not recorded
Inspect measurement evidence →
Lanecli/codexDeliveryDelivery not establishedConditionsUnproven
Model failures0Lane errors0Withheld / invalid0 / 0
Elapsed median123.3 seconds · 10/10 observedSteps median20 · 10/10 observedTokens medianNot recordedCost median (USD)Not recorded
delivery equivalence is unproven; delivery is not proved; lane configuration is not recorded
Inspect measurement evidence →
Model lane
codestral-latest
1/9Certified passes · rate not published
Lanecodestral-latestDeliveryDelivery not establishedConditionsUnproven
Model failures8Lane errors1Withheld / invalid0 / 0
Elapsed median67.5 seconds · 9/9 observedSteps median22 · 9/9 observedTokens median72643 · 9/9 observedCost median (USD)Not recorded
delivery equivalence is unproven; delivery is not proved; lane configuration is not recorded
Inspect measurement evidence →