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 resultLaborBench · accuracy
- Stonewall77.7
- STARA83
- Lexis+ AI64
- Westlaw AI58
Statutory research
LaborBench
- StonewallMeasured · 28 Oct 2026Accuracy77.7%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.
Legal reasoning
LegalBench
- StonewallEvaluation pending
Stonewall has not run this test yet. When it does, the result goes here with its method.
- Claude Fable 5.1Published · Vals AI88.51%
- GPT-5.6 SolPublished · Vals AI86.97%
Method and sources
Published Vals reference results. A Stonewall result must use a comparable task set and scoring method before it can be ranked alongside them.
Stonewall has no measured score or projection on this test yet. An estimate will be labeled separately from a measured result.
Agent work
HLAB-Vals-1.1
- StonewallEvaluation pending
Stonewall has not run this test yet. When it does, the result goes here with its method.
- Claude Opus 5.5Published · Vals AI9.17%
- GPT-6 AstraPublished · Vals AI7.08%
- GPT-6.1 SolPublished · Vals AI6.25%
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.