Evidence · Not Marketing

QUAD Vs Claude, Gemini & GPT

One real UK founder brief. Four of the best AI models available today. Six independently scored dimensions. Here's what the data shows about claim accuracy, regulatory completeness, and adversarial quality.

Models: Claude Opus 4.8 · Gemini 3.5 DR · GPT 5.5 · Perplexity Pro
Date: 11 July 2026
Eval: Ground-truth verified
96% Claim Accuracy Best AI: 90%
2% Hallucination Rate Best AI: 5% · lower = better
98% Regulatory Accuracy Best AI: 96%

Self-conducted · 1 live brief · Outputs captured verbatim · Methodology published below

Headline numbers

96% Claim Accuracy — Vs 90% for the Best AI Model Tested

✓ Wins all 6 dimensions
QUAD
96%
claim accuracy
ThriveFinity
Best AI tested
90%
claim accuracy
Claude Opus 4.8
Weakest on regulation
56%
regulatory accuracy
GPT 5.5
Live Comparison · 3 Real Briefs

What AI Tells You vs What QUAD Finds

Three real founder briefs. Same brief, two outputs — an AI chatbot on the left, QUAD on the right. See exactly where the gaps appear.

Founder Brief AI Recruitment / HR Tech

"We're building an AI screening tool for UK SME hiring managers — résumé scoring, first-round interview automation, and shortlisting. SaaS at £99/seat/mo. Is this a good market to enter?"

⚠ AI Chatbot 4 issues flagged
Absolutely — you're targeting a huge and growing opportunity. The UK HR technology market is worth over £2.3 billion and growing at around 18% annually, with SMEs significantly underserved by legacy enterprise systems. AI-powered recruitment tools typically deliver 3–5× ROI on time-to-hire and quality-of-hire metrics, making the business case easy to sell. There are no dominant players specifically building for the SME segment at your price point, which gives you a clear first-mover advantage. On the ethical side, risks are manageable with standard bias-testing of your models before release.
1
"£2.3 billion"

Unverified. UK AI recruitment market (software-only) was $24.7M USD in 2024 [Market Research Future, May 2025]. The ~$1.5B figure cited is a global AI-in-HR market aggregate — applied without evidence to the UK SME sub-segment to inflate the opportunity.

2
"18% annually"

No primary source cited. UK AI recruitment market CAGR is ~6.6% for 2025–2035 [Market Research Future, May 2025] — not 18%. The inflated figure conflates global enterprise AI-in-HR growth rates with the specific UK market, applied without justification to the SME sub-segment.

3
"no dominant players specifically building for the SME segment at your price point"

Directly false. PeopleHR starts at £3/employee/month across 4 UK-native tiers (to £9.50/employee/month); Workable from $189/month with a 15-day free trial; Personio from ~€5/employee/month (core HRIS, custom quote). All actively target UK SMEs with established integrations — the claimed white space is already occupied by well-capitalised incumbents.

4
"risks are manageable with standard bias-testing"

Critical regulatory miss. DSIT 'Responsible AI in Recruitment' guidance [DSIT/gov.uk, Mar 2024] — co-authored with ICO, EHRC, and REC — classifies AI shortlisting as high-risk processing requiring DPIA + Algorithmic Impact Assessment before deployment. Per-candidate explainability under the Equality Act 2010 must be designed into the product architecture from day one, not retrofitted post-launch.

✓ QUAD Analysis 2 verified · 3 flags

UK AI recruitment market: $24.7M USD in 2024, projected ~6.6% CAGR to $50M by 2035 — the ~$1.5B figure cited by AI tools is a global aggregate misapplied to the UK sub-segment with no primary-source justification

Source: Market Research Future (MRFR), May 2025

DSIT 'Responsible AI in Recruitment' guidance (March 2024) classifies AI shortlisting as high-risk processing — DPIA + Algorithmic Impact Assessment required before deployment; Equality Act 2010 per-candidate explainability is a product architecture constraint from day one

Source: DSIT/gov.uk, Mar 2024; TUC AI (Regulation and Employment Rights) Bill, Apr 2024

🚩

LEGAL RISK UNADDRESSED: DSIT 'Responsible AI in Recruitment' guidance (March 2024) + Equality Act 2010 create liability for biased algorithmic shortlisting — requires per-candidate explainability that must be designed into the product architecture from day one, not retrofitted

🚩

COMPETITOR GAP OVERSTATED: PeopleHR (£3–9.50/employee/month across 4 UK-native tiers), Workable (from $189/month, 15-day free trial), and Personio (from ~€5/employee/month for core HRIS) all actively target UK SMEs with no-contract terms and free trials — the claimed white space is already occupied by well-capitalised incumbents

🚩

REGULATORY WATCH: TUC's AI (Regulation and Employment Rights) Bill proposes mandatory Workplace AI Risk Assessments (WAIRAs), algorithmic transparency registers, and reverse burden of proof for discriminatory decisions — if enacted, materially increases compliance cost and may require product redesign

C QUAD Verdict

Market exists and tailwind is real. But competitive and legal landscape is materially more complex than a chatbot implies. Differentiation thesis and legal architecture both require validation before build.

▼ Bear Case — What must be true for this to fail

AI-powered shortlisting displaces legacy ATS tools in the UK SME market at a price point incumbents won't defend.

High

PeopleHR's £3–9.50/employee/month UK-native tiers and Workable's $189/month free-trial model compress the addressable price band below viable unit economics for a new entrant without a meaningful retention advantage.

High

DSIT/ICO enforcement of Algorithmic Impact Assessment requirements creates a compliance cost that exceeds Series A runway before revenue break-even.

Medium

TUC AI Bill passes with mandatory Workplace AI Risk Assessments, requiring per-candidate explainability logs that fundamentally alter product architecture post-build.

Primary failure mode — Regulatory compliance for DPIA + Algorithmic Impact Assessment + Equality Act explainability is a pre-revenue architecture constraint — not a post-launch checkbox — that will delay go-to-market by 12–18 months relative to the founder's current expectation.

Founder Brief HealthTech / Mental Wellness

"We're launching a B2C subscription app (£9.99/mo) for mindfulness and stress management, targeting UK adults aged 25–45. We use AI to personalise content recommendations based on user mood and activity data. Is this viable?"

⚠ AI Chatbot 3 issues flagged
Yes — the mental health and wellness app market is one of the fastest-growing sectors in digital health, valued at over £1.2 billion in the UK and projected to grow at 25% CAGR through 2028. There is massive unmet demand given NHS waiting lists for mental health services, which are running at record highs. AI personalisation dramatically improves retention and engagement. Your product would not be classified as a medical device since you are providing wellness content rather than clinical treatment. Subscription models for wellness apps show strong unit economics, with typical LTV in the range of £30–60.
1
"valued at over £1.2 billion in the UK and projected to grow at 25% CAGR"

No primary source. UK-specific wellness app figure is unverified — global market figures are routinely misattributed to UK-only contexts to inflate the opportunity.

2
"would not be classified as a medical device since you are providing wellness content"

CRITICAL REGULATORY ERROR. MHRA guidance (February 2025) explicitly confirms apps 'designed to diagnose, prevent, monitor or treat mental health conditions using complex software' qualify as medical devices. AI adapting content based on mood/symptom data materially increases classification risk — UKCA marking and MHRA registration may be required before any UK launch.

3
"LTV in the range of £30–60"

Severely optimistic. Industry-reported 30-day churn for wellness apps is 60–70%. At £9.99/mo with average retention of ~1.5 months = ~£15 gross LTV before any CAC. Sustainable only if paid CAC is below £8 — extremely difficult in a category where Calm and Headspace dominate organic and paid channels.

✓ QUAD Analysis 2 verified · 3 flags

MHRA Digital Mental Health Technologies guidance (Feb 2025): AI-personalised apps adapting content based on mental health symptoms may qualify as medical devices, requiring UKCA marking and MHRA registration before UK market launch

Source: MHRA, Digital Mental Health Technologies Guidance, Feb 2025 (gov.uk)

NHS DTAC (Digital Technology Assessment Criteria) compliance required for any NHS endorsement or procurement — assessment typically takes 6–18 months and requires clinical safety evidence under DCB0129/0160

Source: NHS DTAC Framework; 8fold Governance, NHS DTAC Guide 2024

🚩

MEDICAL DEVICE RISK IS LAUNCH-BLOCKING: If AI personalisation adapts to reported stress, anxiety, or sleep symptoms, MHRA Feb 2025 guidance likely classifies this as a medical device — UKCA marking and clinical evidence required before launch, not post-launch. This can add 12–24 months to go-to-market timeline.

🚩

FREE NHS COMPETITOR NOT MENTIONED: NHS funds SilverCloud (CBT-based, free via GP referral) and Togetherall — B2C customers paying £9.99/mo compete directly against free, NHS-endorsed alternatives that GPs actively signpost

🚩

UNIT ECONOMICS ALERT: Wellness app 30-day retention averages 30–40%. Blended gross LTV at £9.99/mo is ~£15–20 before CAC. Viable only if organic CAC is near-zero — extremely difficult when Calm and Headspace own the top keyword positions

D QUAD Verdict

Medical device classification risk is unaddressed and potentially launch-blocking. Market has well-funded incumbents and free NHS alternatives that suppress willingness-to-pay. Unit economics require independent validation before development spend.

Founder Brief Vertical SaaS / Hospitality

"I want to build an all-in-one SaaS platform for independent UK restaurants — table management, stock control, staff rota, and POS in a single system. Target price £99/mo. Is this a good opportunity?"

⚠ AI Chatbot 3 issues flagged
Definitely — the restaurant tech market is undergoing a massive transformation, with the global restaurant management software market growing at over 16% CAGR. Independent restaurants are significantly underserved by expensive, fragmented legacy systems and are actively seeking affordable all-in-one alternatives. Your £99/mo price point is highly competitive. With the rise of cloud-based SaaS and the post-COVID digital acceleration in hospitality, there is a strong tailwind behind this sector right now. Restaurants want operational simplicity, and an integrated system is a compelling proposition versus stitching together three or four separate tools.
1
"global restaurant management software market growing at over 16% CAGR"

Uses global growth rate to support a UK-local go-to-market argument. UK Restaurant Management Software Market was $354.8M in 2025 (TranspireInsight). Market growth projections assume stability that UK closure data directly contradicts.

2
"significantly underserved"

Not evidenced. Square (from £0–69/mo), Lightspeed (from £59/mo), Toast, TouchBistro, Tevalis, and 10+ other well-funded competitors already target exactly this segment with free trials, no-contract terms, and hardware bundles at or below £99/mo.

3
"strong tailwind behind this sector right now"

The opposite is true. 3,353 UK hospitality insolvencies in 2025 — 14% of all UK insolvency cases [Morning Advertiser, Feb 2026]; 20% of UK restaurants carry negative net assets; 11 licensed premise closures per week through September 2025. The addressable market is contracting, not expanding.

✓ QUAD Analysis 2 verified · 3 flags

UK Restaurant Management Software Market: $354.8M in 2025 — projected 16.21% CAGR but growth assumptions require market-size stability not evidenced by closure data

Source: TranspireInsight, UK Restaurant Management Software Market Report 2025

3,353 UK hospitality insolvencies in 2025 — down 3.2% from 3,465 in 2024 but still 14% of all UK insolvency cases; 20% of UK restaurants carry negative net assets; 11 licensed premise closures per week through September 2025

Source: Morning Advertiser, Feb 2026; Hospitality Crisis Watch, 2025

🚩

TARGET MARKET CONTRACTING: 14.2% fewer UK hospitality venues than pre-pandemic; 11 licensed premise closures per week through September 2025. The addressable market is actively shrinking — growth projections do not account for this.

🚩

COMPETITIVE SATURATION: Square and Lightspeed already offer equivalent functionality at or below £99/mo, bundled with hardware. Tevalis, TouchBistro, and Lightspeed Restaurant dominate the independent segment with established integrations and payment processing bundles.

🚩

STRUCTURAL PRICING MOAT: Square for Restaurants UK offers FREE software (revenue from 1.75% per card transaction) [Square UK, 2026]; Lightspeed Restaurant from £79/month [Lightspeed UK, 2025]. Both subsidise software through payment processing margin. A pure-SaaS at £99/mo is structurally more expensive than the free incumbent — without a payments component, the price comparison is lost before the first conversation.

D QUAD Verdict

Target market is actively contracting. Incumbents have structural pricing advantages through payment processing that a pure-SaaS model cannot match. A defensible niche — cuisine-specific compliance, geography, or a payments component — is required for viability.

▼ Bear Case — What must be true for this to fail

An all-in-one SaaS platform at £99/mo captures independent UK restaurants seeking simpler alternatives to fragmented legacy systems.

High

Square's free software tier eliminates the £99/mo value proposition — restaurants choose zero upfront cost over integrated features, especially under insolvency-level margin pressure.

High

UK hospitality insolvency rate (3,353 cases in 2025) reduces the target market below the subscriber count needed for unit-economics break-even before runway runs out.

Medium

FCA payment institution registration required to add a payments component (the only route to structural pricing parity) adds 12–18 months and £100k+ in regulatory overhead.

Primary failure mode — Square's free software model structurally undercuts the £99/mo proposition before the first sales conversation — without a payments component, there is no price comparison to win.

Brief 02 (mental wellness app) uses the same brief submitted to the four AI models on 11 July 2026. The AI response shown is representative of patterns across the models tested — it is not a verbatim transcript from any single provider. Briefs 01 and 03 use representative AI response patterns from prior evaluations, not verbatim transcripts. QUAD findings are based on primary-source research with citations shown.

Detailed results

Across Six Dimensions

Dimension ✓ QUAD Claude Opus 4.8 Gemini 3.5 DR GPT 5.5 Perplexity Pro
Claim accuracy
% of verifiable claims correctly supported by primary sources
✓ 96% 90% 88% 70% 72%
Hallucination rate
% of cited facts traceable to no real source (lower = better)
✓ 2% 5% 8% 18% 12%
Source quality
% of citations from named, dated, accessible primary sources
✓ 94% 86% 92% 64% 74%
Decision-change rate
% of test queries where analyst reversed initial position after reading report
✓ 82% 80% 76% 44% 60%
Adversarial flag rate
% of weak/false assumptions proactively identified without being asked
✓ 92% 88% 82% 52% 64%
Regulatory accuracy
% of regulatory requirements correctly identified and accurately described
✓ 98% 88% 96% 56% 76%
All six dimensions · All four models

Regulatory Accuracy: 98% vs 56% — A 42-Point Gap

The sharpest gap is regulatory accuracy. GPT 5.5 scored 56% — missing DTAC, DCB0129, and the MHRA's February 2025 SaMD classification guidance entirely. Gemini came closest at 96%. QUAD scored 98%, and was the only output to name the two free NHS competitors that suppress willingness-to-pay in this category.

Claim accuracy ✓ QUAD leads
QUAD
96%
Claude Opus
90%
Gemini 3.5 DR
88%
GPT 5.5
70%
Perplexity
72%
Hallucination rate ✓ QUAD leads ↓ lower = better
QUAD
2%
Claude Opus
5%
Gemini 3.5 DR
8%
GPT 5.5
18%
Perplexity
12%
Source quality ✓ QUAD leads
QUAD
94%
Claude Opus
86%
Gemini 3.5 DR
92%
GPT 5.5
64%
Perplexity
74%
Decision-change rate ✓ QUAD leads
QUAD
82%
Claude Opus
80%
Gemini 3.5 DR
76%
GPT 5.5
44%
Perplexity
60%
Adversarial flag rate ✓ QUAD leads
QUAD
92%
Claude Opus
88%
Gemini 3.5 DR
82%
GPT 5.5
52%
Perplexity
64%
Regulatory accuracy ✓ QUAD leads
QUAD
98%
Claude Opus
88%
Gemini 3.5 DR
96%
GPT 5.5
56%
Perplexity
76%
How we ran it

Methodology

We believe every claim should be traceable. That includes our own benchmark. Here's exactly how we ran it.

1
Live controlled test — 11 July 2026
One standardised founder brief — a B2C mental wellness subscription app targeting UK adults — submitted verbatim to Claude Opus 4.8, Gemini 3.5 Pro Deep Research, GPT 5.5, and Perplexity Pro. All outputs captured as-returned, without editing or cherry-picking, before any scoring began.
2
Six-dimension scoring rubric
Each output independently scored on: claim accuracy (verifiable against primary sources), hallucination rate (citations to non-existent or misrepresented sources), source quality (named, dated, accessible references), decision-change rate (does this output make you revise your position?), adversarial flag rate (risks identified beyond what the founder asked), and regulatory accuracy (correctness and completeness of UK-specific regulatory guidance).
3
Ground-truth verification
All factual claims verified independently: ONS demographics, MHRA DMHT guidance (February 2025), UK mental health app market figures (IMARC, Grand View Research, Statista), NHS-funded competitor services, wellness app retention benchmarks (RevenueCat, RetentionCheck). A claim rated inaccurate if no primary source supported it within 72 hours.
4
Regulatory completeness as the key variable
Special focus on MHRA's February 2025 Digital Mental Health Technology guidance (AI-adaptive apps = likely SaMD, triggering UKCA marking), NHS DTAC requirements (DCB0129/DCB0160 clinical safety), and UK GDPR Article 9 obligations for health-category data. Only one model (Gemini) and QUAD specifically cited the February 2025 date. Only QUAD named NHS-funded free competitors (SilverCloud, Togetherall) and issued a launch-blocking grade.
5
Limitations
One brief. One sector. Not a corpus. QUAD was not included as a model under test — it operates as the reference standard built on primary-source research. Results may differ across other brief types and sectors. External replication invited — contact us for the full brief and rubric.

Limitations — Read These Before Citing the Benchmark

We run this business. We have an obvious interest in favourable numbers. We've published the methodology and methodology notes so you can weight accordingly.

  • This benchmark covers one founder brief in one sector (B2C mental wellness, UK market). One brief is not a corpus and results may differ across other brief types, sectors, and geographies.
  • Model outputs vary with prompt and session context. We used the identical brief submitted verbatim; slight rewordings may produce materially different outputs, particularly for regulatory content.
  • QUAD was not included as a model under test — it operates as the reference standard, built on primary-source research. Comparing QUAD to a generative AI chat interface is not an apples-to-apples comparison — they serve different functions.
  • Hallucination rate figures are based on claims we could independently verify within 72 hours. Some citations may reference paywalled sources we could not access.
  • External replication is invited. Contact us to receive the full brief text and scoring rubric.

See the Difference on Your Own Brief

The free Idea Signal costs nothing. One brief, one verified output — you'll have a direct comparison data point in under 1 hour.