Benchmarks

77.7% on Stanford’s LaborBench.

One run of Stonewall’s harness on Claude Opus 5.5 across 1,647 statutory questions: above published Lexis+ AI and Westlaw AI, below the study’s STARA.

See the full result

LaborBench · accuracy

  1. Stonewall77.7
  2. STARA83
  3. Lexis+ AI64
  4. Westlaw AI58
Percent correct. Stonewall measured 28 Oct 2026; the others as the study published them. Accuracy: 13.7 points above Lexis+ AI, 19.7 above Westlaw AI, 5.3 below STARA.

Statutory research

LaborBench

Accuracy and F1 · %
  • StonewallMeasured · 28 Oct 2026
    Accuracy77.7%
    F176.9%
  • STARAPublished · Afane et al.
    Accuracy83%
    F181%
  • Lexis+ AIPublished · Afane et al.
    Accuracy64%
    F141%
  • Westlaw AIPublished · Afane et al.
    Accuracy58%
    F164%

Afane et al. · CSLAW 2026 · Table 1

Method and sources

Published study of 1,647 statutory questions, using the same uncorrected DOL labels. F1 is one score that falls when the system misses provisions that exist or asserts ones that do not. These are study results, not a current-product retest; Westlaw received compressed context.

Stonewall’s result is measured, not estimated: one complete local Shelby harness run on 28 Oct 2026 with Claude Opus 5.5 at high effort, all 1,647 questions graded against the same DOL labels with the same metrics. 95% bootstrap intervals: accuracy 75.7–79.8%, F1 74.5–79.1%. This measures the harness, not the deployed application. Stonewall answered without a statute database. LaborBench has been public since May 2025, so the model may have seen it in training. The study rows are the study’s published results, not a same-day retest. STARA remains ahead.

Agent work

HLAB-Vals-1.1

Task pass rate · %
  • StonewallEvaluation pending

    Stonewall has not run this test yet. When it does, the result goes here with its method.

  • Claude Opus 5.5Published · Vals AI
    9.17%
  • GPT-6 AstraPublished · Vals AI
    7.08%
  • GPT-6.1 SolPublished · Vals AI
    6.25%

Vals AI · 26 Oct 2026

Method and sources

Harvey created this benchmark; these are model scores, not a score for the Harvey product. Vals version 1.1 results are not comparable with the archived v1 board or the independent LAB-AA evaluation.

Stonewall has no measured score or projection on this test yet. An estimate will be labeled separately from a measured result.

Harvey’s own product evaluation uses a different method and cannot share this ranking.

See Shelby answer from the record