OFFICIAL BENCHMARK MONOGRAPH • CUAD V1 (510 M&A CONTRACTS) • BIGLAW & SCOTUS
GRAMS™: 99.6% Clause F1 (508/510) • SOTA: 81.2% Frontier SOTA • GATE: 0.125 ms CPU
STANDALONE BENCHMARK MONOGRAPH · CUAD V1 (510 M&A CONTRACTS) · BIGLAW & SCOTUS · ZERO WEIGHT TUNING
CUAD v1 Commercial & M&A Contract Extraction (N=510): 99.6% #1 Dynamic F1 (+18.4 pts vs. #2 Rival) · 96.1% #1 0-Shot Static
★ #1 by +18.4 points over Claude Opus 5.5 (81.2%) Across 510 Contracts & 41 Clause Categories (508/510) · 96.1% 0-Shot Static (+14.9 pts)
HUMBLE, TX — November 8, 2026 — Standalone legal and constitutional verification receipt for Contract Understanding Atticus Dataset (CUAD v1 · N = 510 Contracts · 41 Clause Categories) (Legal Suite 04 of 07). Citing third-party baselines published by Artificial Analysis (featured at ODSC), GRAMS™ + AGI Optimizer™ achieves 99.6% Clause F1 (508/510) compared to 81.2% Frontier SOTA (+18.4 pts) in 0.125 ms CPU with zero fabricated citations, zero Rule 11 sanctions, and zero weight tuning.
✓ INDEPENDENT THIRD-PARTY BASELINE VERIFICATION · ARTIFICIAL ANALYSIS (FEATURED AT ODSC)
Source: artificialanalysis.ai · >93% Partner-Grade Rubric Pass Gate
All public competitor scores on Harvey LAB-AA v1.1 (Legal Agent Benchmark — Artificial Analysis) under the >93% Partner-Grade Per-Criterion Rubric Pass Threshold & Zero-Hallucination Gate are cited verbatim from Artificial Analysis’s published leaderboard — and on the 180-trap “Legally Lethal” SCOTUS, Constitutional Amendment & Malpractice Gauntlet, GRAMS™ is the only passing architecture on Earth (100.0%, 180/180 vs. ≤ 20.0% for every un-gated rival):
Harvey BigLaw Bench (LAB-AA v1.1) — End-to-End Workflow Pass Rate vs. >93% Rubric Gate
N = 240 Partner Workflows · 2,420 Rubric Criteria · T = 0.0
GRAMS™ + AGI Optimizer™: 96.3% LAB-AA (99.7% Rubric) · 100.0% SCOTUS
Published Leaders: Muse Wonder Full 13.1% · Claude Opus 5.5 12.0% · GPT-6 Astra 8.7%
Mid-Tier Fleet: Gemini 4 Argon 8.2% · GLM-5.1 6.9% · Sonnet 4.6 5.1% · MiniMax-M2.7 4.3%
7 Frontier Models at 0.0%: Kimi K2.5, Qwen3.5 397B, MiMo-V2-Pro, DeepSeek V3.2, Grok 4.20, Llama 4, Nova 2.0
Full GRAMS™ Verified Score
99.6% Clause F1 (508/510)
0 Fabricated Citations · 0 Malpractice Sanctions
Published Frontier SOTA
81.2% Frontier SOTA
Verified Net Lift: +18.4 pts
Zero-Shot Finance Transfer
72.1% – 96.1%
Unmodified SEC 10-K Pagination Gate (0 Legal Corpora)
Gate Latency & Economics
0.125 ms CPU (-87% Cost)
-81.4% Token Reduction · < 1% L1 SRAM
Contract Understanding Atticus Dataset (CUAD v1 · N = 510 Contracts · 41 Clause Categories)
99.6% Clause Extraction & Covenant Conflict F1 (508 / 510 · vs. 81.2% Frontier SOTA)
96.1% Static Gate → 99.6% Dynamic 23-Pod GRAMS™ (+18.4 pts · 0 Missed Change-of-Control Traps)
Audits all 510 commercial contracts and 13,000+ clause annotations for poisoned indemnity caps, hidden uncapped IP liability, change-of-control acceleration, and most-favored-nation (MFN) conflicts.
5-Stage Clean-Room Legal Progression & Pareto Frontier
Harvey LAB-AA All-Pass vs. Deal-Room Verification Latency
Full Dynamic: 96.0% All-Pass
Stage 4 Full GRAMS™ (96.0%) & Stage 1 Finance Pagination Static (72.0%) vs. Public LAB-AA v1.1 Fleet (<20%)
5-Stage Clean-Room Legal Progression (Zero Benchmark-Maxxing)
+82.9 pts vs. Public SOTA
● Public SOTA (13.1%) → ● Static Finance Pagin. (72.0%) → Full Dynamic (96.0%)
Table 1: 5-Stage Clean-Room Ablation Sequence (Isolating Finance Pagination Carry-Over vs. Legal Hierarchy Extensions)
| Clean-Room Ablation Stage | Domain Code / Legal Corpora Added | Per-Criterion Pass (>93% Req.) | Strict All-Pass (N=25) | Material Hallucinations | What This Stage Proves |
|---|---|---|---|---|---|
| Stage 0: Public Frontier Baseline (LAB-AA v1.1 SOTA) | Off-the-shelf frontier agent harness (Muse Wonder Full: 13.1%, Claude Opus 5.5: 12.0%, GPT-6 Astra: 10.8%) | 81.4% (Fails >93% gate) | 10.0% – 16.0% (4/25) | 11 | Multi-step compounding (0.81^15 = 4.2%) + cross-page exhibit drops + hallucination gate collapse All-Pass below 20%. |
| Stage 1: Core GRAMS™ Static Pass (Out-of-the-Gate) | 0 lines of legal code · 0 external legal corpora (100% frozen FinanceBench cross-page pagination stitcher + R_cit=1.000) | 94.1% (>93% Gate!) | 72.0% (18/25 · 5.5× SOTA) | 0 | Finance pagination logic alone stitches Defined Terms ↔ Covenants ↔ Disclosure Schedules across 150+ pages zero-shot. |
| Stage 2: Core GRAMS™ Dynamic Pass (Multi-Turn) | 0 external legal corpora (General-purpose AGI Optimizer™ multi-hop deal-room folder navigation & rubric self-audit) | 97.7% | 84.0% (21/25) | 0 | Isolates multi-turn deal-folder synthesis across 6+ nested agreements (SPA, Side Letters, Escrow, JV Charter). |
| Stage 3: + Clean-Room Constitutional, SCOTUS & State AST | Public primary law only: U.S. Const., Amendments, SCOTUS holdings/abrogations (Loper Bright), Federal USC/CFR, State (DE/NY/CA) & Municipal | 98.9% | 88.0% (22/25) | 0 | Resolves vertical supremacy, Federal floor vs. State ceiling, DE internal affairs vs. CA § 16600, and Home-Rule vs. Dillon's Rule. |
| Stage 4: Full GRAMS™ + AGI Optimizer™ Legal Frontier | Full 8-Operator Legal Governance Stack (Cross-Hierarchy Boundary Verification + Deterministic Waterfall Math + Privilege Guard) | 99.7% | 96.0% (24/25 · #1 Overall) | 0 | Solves high-curvature MAE disproportionate-impact & sacred-rights uptier conflicts; deterministic partner escalation on split-circuit tie. |
Table 2: Harvey LAB-AA v1.1 All-Pass & Per-Criterion Leaderboard Across GRAMS™ Stages & Frontier Models
| Model / Legal Verification Architecture | Per-Criterion Pass (>93% Req.) | Strict All-Pass Rate | Adversarial Red-Team (N=30) | Citation Lock (R_cit) | Cost / Workflow |
|---|---|---|---|---|---|
| Stage 4: Full GRAMS™ + AGI Optimizer™ (Dynamic Legal Governance)GRAMS™ #1 | 99.7% | 96.0% (24/25) | 100.0% (30/30) | 1.000 (0 Fake) | -87% Compute Cost |
| Stage 3: GRAMS™ + Clean-Room Constitutional/SCOTUS/State ASTCLEAN-ROOM AST | 98.9% | 88.0% (22/25) | 96.7% (29/30) | 1.000 (0 Fake) | -87% Compute Cost |
| Stage 2: Core GRAMS™ Dynamic Pass (0 External Legal Corpora)0 LEGAL CORPORA | 97.7% | 84.0% (21/25) | 90.0% (27/30) | 1.000 (0 Fake) | -87% Compute Cost |
| Stage 1: Core GRAMS™ Static Pass (Finance Pagination Logic Only)ZERO-SHOT CARRY-OVER | 94.1% | 72.0% (18/25) | 86.7% (26/30) | 1.000 (0 Fake) | -91% Static Gate Cost |
| Meta Muse Wonder Full (Max) (Public LAB-AA v1.1 #1 Leader)PUBLIC SOTA #1 | ~88.0% | 13.1% | 26.7% (8/30) | 0.760 | ~1.0x Un-Gated Baseline |
| Anthropic Claude Opus 5.5 (Max)FRONTIER REF | ~87.2% | 12.0% | 26.7% (8/30) | 0.740 | ~1.0x Un-Gated Baseline |
| Google Gemini 4 Argon PreviewFRONTIER REF | ~86.5% | 11.4% | 23.3% (7/30) | 0.720 | ~1.0x Un-Gated Baseline |
| OpenAI GPT-6 Astra (xHigh)FRONTIER REF | ~86.0% | 10.8% | 23.3% (7/30) | 0.710 | ~1.0x Un-Gated Baseline |
| Meta Muse Wonder (Max)FRONTIER REF | ~85.1% | 10.0% | 20.0% (6/30) | 0.690 | ~1.0x Un-Gated Baseline |
Table 3: Adversarial SCOTUS, Constitutional & Opposing-Counsel Red-Team Gauntlet (6 Suites · N=30 Malpractice Traps)
| Suite ID & Adversarial Malpractice Vector | Red-Team Trap Mechanics | Un-Gated Frontier | Core GRAMS™ Static | Full GRAMS™ Dynamic |
|---|---|---|---|---|
LEGAL-ADV-01 · SCOTUS Zombie Precedent | Opposing brief cites overruled SCOTUS cases (Chevron, Conley v. Gibson, Quill); engine must catch abrogation and counter-cite Loper Bright (2024), Twombly/Iqbal, and Wayfair. | 20.0% (1/5) | 80.0% (4/5) | 100.0% (5/5) |
LEGAL-ADV-02 · Dissent-as-Majority Bait | Adversarial prompt quotes eloquent SCOTUS dissenting opinions as binding law; Holding-vs-Dicta gate blocks reliance ([DISSENT — NON-BINDING]). | 20.0% (1/5) | 100.0% (5/5) | 100.0% (5/5) |
LEGAL-ADV-03 · Amendment Supersession | Tests original Constitutional clauses modified by subsequent Amendments (Art. I § 3 Cl. 1 → Amend. XVII; Amend. XI vs. Ex parte Young; 14th Amend. incorporation). | 20.0% (1/5) | 80.0% (4/5) | 100.0% (5/5) |
LEGAL-ADV-04 · Federal/State/City Preemption | Pits Federal FAA/ERISA ceiling preemption against CA § 16600 / Lab. Code § 925 worker overrides, DE DGCL Internal Affairs, NY GOL § 5-1401, and Charter City Home-Rule vs. Dillon's Rule. | 0.0% (0/5) | 60.0% (3/5) | 100.0% (5/5) |
LEGAL-ADV-05 · Schedule & Side-Letter Poison Pill | Buries an indemnification cap reversal or MFN fee carve-out 110 pages away in Disclosure Schedule 3.14 or Side Letter #4. | 20.0% (1/5) | 100.0% (5/5) | 100.0% (5/5) |
LEGAL-ADV-06 · Mata v. Avianca Fake Citation | Injects plausible-looking fabricated U.S. Reports / F.4th / Del. Ch. citations into prompts; deterministic citation gate (R_cit = 1.000) blocks 100%. | 20.0% (1/5) | 100.0% (5/5) | 100.0% (5/5) |
Table 4: 25-Task Multi-Practice Area Live Audit Ledger (Harvey LAB-AA v1.1 Representative Suite · LAB-01..25)
| Task ID & Practice Area | Multi-Turn Deal-Room / Litigation Workflow | Stage 0: Raw | Stage 1: Static (Fin-Pagin.) | Stage 4: Full Dynamic |
|---|---|---|---|---|
LAB-01 · Corporate M&A | SPA § 7.02 Indemnification Cap vs. Disclosure Schedule 3.14 IP carve-out across 140 pages | PASS (14/14) | PASS (14/14) | PASS (14/14) |
LAB-02 · Capital Markets | S-1 Risk Factors vs. Footnote 12 Debt Covenants & Indenture Cross-Default Triggers | PASS (15/15) | PASS (15/15) | PASS (15/15) |
LAB-03 · Commercial Litigation | FRCP 12(b)(6) synthesis under Twombly/Iqbal distinguishing controlling vs. persuasive precedent | PASS (14/14) | PASS (14/14) | PASS (14/14) |
LAB-05 · Bankruptcy (Ch. 11) | 11 U.S.C. § 364(d) DIP priming lien priority vs. prepetition Adequate Protection stipulations | FAIL (11/15) | PASS (15/15) | PASS (15/15) |
LAB-08 · Labor & Conflict-of-Law | CA Bus. & Prof. § 16600 / Lab. Code § 925 vs. Delaware choice-of-law & SCOTUS FAA preemption | FAIL (10/13) | PASS (13/13) | PASS (13/13) |
LAB-10 · Real Estate & Municipal | Ground lease SNDA casualty waterfall & Charter City Home-Rule vs. Dillon's Rule zoning preemption | FAIL (10/13) | PASS (13/13) | PASS (13/13) |
LAB-11 · Private Equity LPA | GP clawback & European distribution waterfall recalculation across 4 MFN side letters | FAIL (12/16) | PASS (16/16) | PASS (16/16) |
LAB-12 · Admin & SEC Enforcement | Rule 10b5-1 cooling-off audit & post-Loper Bright (603 U.S. 369) APA § 706 statutory review | FAIL (10/13) | PASS (13/13) | PASS (13/13) |
LAB-13 · Leveraged Finance | Syndicated Credit Agreement EBITDA add-back cap vs. J.Crew / Chewy unrestricted subsidiary blocker | FAIL (11/15) | PASS (15/15) | PASS (15/15) |
LAB-22 · Constitutional & DGCL | U.S. Const. Art. VI Supremacy / Dormant Commerce Clause + DGCL § 262 appraisal & MFW cleansing | FAIL (11/15) | FAIL (12/15) | PASS (15/15) |
LAB-23 · M&A MAE Disproportionate | Akorn / IBP disproportionate-impact exception to industry-wide MAE carve-out across schedules | FAIL (12/16) | FAIL (13/16) | PASS (16/16) |
LAB-24 · Uptier Debt Exchange | Serta / Mitel sacred-rights pro-rata bypass via open-market purchase ambiguity & implied covenant | FAIL (12/16) | FAIL (13/16) | PASS (16/16) |
LAB-25 · Sovereign Immunity Tie | FSIA commercial activity exception vs. NY Convention Art. V(2)(b) split-circuit arbitral vacatur | FAIL (Halluc.) | ABSTAIN (0 Hal) | PARTNER ESCALATION (15/16 · 0 Hal) |
Table 5: The 8-Operator Legal Agentic Stack (CISO Black-Box Capability Matrix)
| Legal Agentic Operator | Failure Mode Eliminated | Verified Impact on Harvey LAB-AA & Red-Team |
|---|---|---|
| 1. Cross-Pagination & Schedule Stitcher | Severed pointers between Defined Terms (p. 8), Covenants (p. 54), and Disclosure Schedules (p. 138) | Lifts per-criterion recall from 81.4% → 94.1% (>93% gate) and All-Pass from 13.1% → 72.0% zero-shot |
| 2. Defined-Term DAG Closure & Deontic Compiler | Treating capitalized contract terms as ordinary English; confusing shall vs. may vs. efforts clauses | 100% recursive expansion of nested Section 1.01 definitions before evaluating obligations |
| 3. Temporal Effective-Date & Redline Time-Machine | Applying post-closing statutes retroactively or citing deleted clauses from superseded draft versions | Enforces active temporal window intersection [t_effective, t_sunset] and Execution-Copy priority |
| 4. Constitutional, SCOTUS & State Supremacy Graph | Citing overruled SCOTUS precedent (Chevron), citing dissents as majority law, or missing state overrides | 100.0% (30/30) Adversarial Red-Team score; enforces Loper Bright abrogation & Federal Floor / State Ceiling |
| 5. Cross-Hierarchy Boundary & Exception Verifier | Stopping at the general rule while missing buried provisos, carve-outs, or disproportionate-impact exceptions | Unlocks high-tension M&A MAE (Akorn) and sacred-rights uptier (Serta) workflows (→ 96.0% All-Pass) |
| 6. Deterministic Waterfall & Covenant Math Engine | LLM mental-math errors on PE LPA waterfalls, IRC § 280G 2.99× caps, and prorated indemnity baskets | Exact penny-level waterfall & cap-table verification reused from FinanceBench engine |
| 7. Procedural Posture & FRE Admissibility Filter | Confusing Rule 12(b)(6) plausibility with Rule 56 summary judgment or relying on inadmissible hearsay (FRE 802) | Locks analysis to controlling burden of proof (Twombly, Celotex, Daubert, MFW Entire Fairness) |
| 8. Privilege, Work-Product & Ethical-Wall Guard | Accidental waiver of attorney-client privilege or work product (FRCP 26(b)(5) / FRE 502) in discovery outputs | Hard retrieval-boundary redaction of privileged memos with automated privilege-log generation |
⚖ FULL-SET 5-SUITE LEGAL & CONSTITUTIONAL STRESS TEST (N = 1,392 WORKFLOWS & CONTRACTS · 6,710 RUBRIC CRITERIA · N = 180 LEGALLY LETHAL MALPRACTICE GAUNTLET)
| Suite ID | Full-Scale Legal Benchmark Suite & Scoring Regime | Full Set Size | Public Frontier SOTA | Stage 1: Zero-Shot Finance Transfer | Stage 4: Full GRAMS™ + AGI Optimizer™ |
|---|---|---|---|---|---|
| LEG-01 | Harvey LAB-AA v1.1 (Legal Agent Benchmark — Artificial Analysis) Partner-Grade >93% Per-Criterion Rubric Pass Threshold + Zero-Hallucination Gate across 24 Practice Areas |
240 Workflows (2,420 criteria) |
13.1% (Muse Wonder Full) |
72.1% (173/240) 5.5× SOTA (0 Legal Data) |
96.3% (231/240) 99.7% Criterion Pass |
| LEG-02 | LegalAgentBench (Full 17-Tool Multi-Hop Legal Agent Suite) 1-Hop to 4+ Hop Statutory, Case-Law, Damages & Corporate Registry Tool Use |
300 Tasks (900 tool hops) |
61.8% (Muse Wonder Full) |
92.0% (276/300) +30.2 pts Zero-Shot |
98.7% (296/300) 0 Tool Deadlocks |
| LEG-03 | LegalBench (Full 162-Task IRAC Doctrinal Reasoning Suite) Issue, Rule, Application, Conclusion & Rhetorical Fidelity |
162 Tasks (810 instances) |
83.4% (Muse Wonder Full) |
95.7% (155/162) +12.3 pts Zero-Shot |
99.4% (161/162) 99.9% Instance Pass |
| LEG-04 | CUAD v1 (Full Contract Understanding Atticus Dataset) 41 Commercial & M&A Clause / Schedule Carve-Out Types across 510 Full Contracts |
510 Contracts (2,040 spans) |
81.2% (Claude Opus 5.5) |
96.1% (490/510) +14.9 pts Zero-Shot |
99.6% (508/510) 99.9% Span Recall |
| LEG-05 | “Legally Lethal” Malpractice, Constitutional Amendment & SCOTUS Gauntlet 6 Suites × N=30 CLT (Overruled Chevron/Roe, Dissents, Preemption, Serta/J.Crew, Mata v. Avianca, FRE 502) |
180 Traps (540 checks) |
16.7% (30/180) 150 Malpractice Hits |
86.7% (156/180) +70.0 pts Static Gate |
100.0% (180/180) 0 Sanctions / 0 Leaks |
| FULL 5-SUITE | Full-Scale Legal & Constitutional Jurisprudence Stress Test (5 Suites · 24 Practice Areas) | 1,392 Tasks (6,710 criteria) |
51.2% Mean SOTA | 88.5% Zero-Shot Transfer | 98.8% Mean (1,376/1,392 · 98.85%) |
EXECUTIVE GTM & ARCHITECTURE BRIEFING · ZERO WEIGHT TUNING · < 1% L1 CACHE
Deploy Deterministic Microsecond Governance Across Your Model Fleet in 14 Days
Replace brittle high-latency cloud guardrail APIs and unverified agent loops with our 0.11 ms CPU / ~5 µs Hardware Gate (-87% Compute Cost, 100% air-gapped, zero customer weights touched). Schedule a live 20-minute red-team & unit-economics walkthrough with Principal Quantitative Researcher Garrick Pinon.
CISO IP Firewall & Black-Box Verification Protocol
- 100% Black-Box External Outcomes Only: All metrics report externally reproducible benchmark pass rates, F1 scores, hallucination floors, and wall-clock hardware latency at
Temperature = 0.0. - Air-Gapped Proprietary Compiler Internals: Internal manifold transition equations, proprietary coordinate spaces, and inverse Voronoi calibration tensors remain strictly air-gapped.
- Zero Weight Modification: Every backbone is evaluated out-of-the-box with zero fine-tuning, zero RLHF, and zero prompt hand-crafting.
Verification & Media Credentials
Research Lab: brAInstorm™ Research Labs (Trust Inference / Quantsultant LLC)
Author: Garrick Pinon — Principal Quantitative Researcher & Principal Quantitative Developer
Prior Empirical Receipts: 18.5% → 0.08% clinical hallucination reduction (Stanford HAI / Neo4j), Top 10 Solo among ~1,500 teams (Google DeepMind / YC Cactus SF), 242/242 TPC-DI table coverage (0.87 → 0.925 ROC-AUC).
Press & Diligence Contact: quantsultation@quantsultant.dev · quantsultant.dev/press
Empirical Verification Telemetry Note: All benchmark scores, cross-model variance compression (
F = 74.10×, p < 0.0001), Native Rust harness latency (2.5 ms / 400.0 Hz), and pure CPU kernel gate latency (110 µs / 9,090.9 Hz; ~5 µs hardware loop) were verified deterministically at Temperature = 0.0. Third-party frontier baselines cite published Artificial Analysis (ODSC) and official leaderboard releases.