Skip to content
Rival
Models
CompareBest ForArena
Sign Up
Sign Up

Compare AI vibes, not scores. Side-by-side outputs across the world's best models.

@rival_tips

Explore

  • Compare Models
  • All Models
  • Leaderboard
  • Challenges

Discover

  • AI Creators
  • AI Tools
  • The Graveyard

Developers

  • Developer Hub
  • MCP Server
  • .llmignore
  • Badges
  • RIVAL Datasets

Connect

  • Methodology
  • Sponsor
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed
© 2026 Rival
Rival
Models
CompareBest ForArena
Sign Up
Sign Up

Compare AI vibes, not scores. Side-by-side outputs across the world's best models.

@rival_tips

Explore

  • Compare Models
  • All Models
  • Leaderboard
  • Challenges

Discover

  • AI Creators
  • AI Tools
  • The Graveyard

Developers

  • Developer Hub
  • MCP Server
  • .llmignore
  • Badges
  • RIVAL Datasets

Connect

  • Methodology
  • Sponsor
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed
© 2026 Rival
  1. Home
  2. Models
  3. GPT-5.2
  4. Advanced Investment Memo (IC Memo)

See how GPT-5.2 compares on this challenge:

  • GPT-5.2 vs Claude Sonnet 4.6
  • GPT-5.2 vs Gemini 3.1 Pro Preview
  • GPT-5.2 vs Z.ai: GLM 5

4 models have responded to the "Advanced Investment Memo (IC Memo)" challenge. Compare their approaches side-by-side on RIVAL. This response is part of RIVAL's open dataset of 5,600+ AI model responses.

Rival
Models
CompareBest ForArena
Sign Up
Sign Up
Back to GPT-5.2

Advanced Investment Memo (IC Memo)

Gpt 5 2's response to the 'Advanced Investment Memo (IC Memo)' challenge.

GPT-5.2
February 8, 2026
Text

?
Prompt

You are writing an internal investment committee memo for a long/short equity fund. Company (fictional): LedgerLift (ticker: LLLT) – B2B spend management + AP automation SaaS for mid-market enterprises. Use only the information below. Do NOT browse the web. This is a fictional exercise, not investment advice. DATA - Current share price: $46 - Shares outstanding (basic): 190m - Net cash: $1.4B - FY2023 revenue: $560m - FY2024 revenue: $680m - FY2025 revenue: $820m - FY2025 gross margin: 78% - FY2025 operating margin: 18% - Revenue mix: 92% subscription, 8% services (services GM ~25%, subscription GM ~82%) - Customer KPIs: 6,200 customers; ARPA ~$132k; logo churn 6%/yr; gross retention 94%; NRR 123% - CAC payback: 18 months; S&M as % of revenue: 34% in FY2025 - Concentration: top 10 customers = 16% of revenue; top 1 = 3% - D&A: 2.5% of revenue - Capex: 3.0% of revenue - Net working capital investment: 1.0% of incremental revenue - Cash tax rate: 23% VALUATION ASSUMPTIONS (build 2026-2030 forecasts) Base case: - Revenue growth: 21%, 18%, 15%, 13%, 12% - Gross margin: 79%, 80%, 80%, 81%, 81% - Operating margin: 20%, 22%, 24%, 25%, 26% - WACC: 10%, terminal growth: 3% Bull case: - Revenue growth: 25%, 21%, 18%, 15%, 13% - Gross margin: 80%, 81%, 82%, 82%, 83% - Operating margin: 21%, 24%, 26%, 28%, 29% - WACC: 9%, terminal growth: 4% Bear case: - Revenue growth: 16%, 13%, 11%, 10%, 9% - Gross margin: 78%, 78%, 79%, 79%, 80% - Operating margin: 17%, 18%, 19%, 20%, 21% - WACC: 12%, terminal growth: 2% COMPS (fictional peer set) - Peer A: EV/NTM Revenue 9.0x, EV/NTM EBIT 35x - Peer B: EV/NTM Revenue 7.0x, EV/NTM EBIT 28x - Peer C: EV/NTM Revenue 11.0x, EV/NTM EBIT 42x Use the median multiple as your comps anchor, but explain adjustments. TASK Write a pro-level IC memo with: 1) Recommendation (Long/Short/Pass) + 12-month PT range + 2-sentence thesis 2) Business + why it wins / why now 3) KPI quality check (NRR, churn, CAC payback, concentration) and what could be wrong 4) Base/Bull/Bear model: show a compact table for 2026-2030 revenue, EBIT, and unlevered FCF; compute DCF EV, equity value, and implied value per share for each scenario (show key steps, not every line) 5) Comps cross-check: implied EV and per-share range using median multiples 6) Catalysts (3), Risks (5), and "what would change my mind" (3 falsifiable triggers) 7) 10 diligence questions for management Keep the memo under ~1,200 words, excluding tables.

GPT-5.2
Response

gpt-5.2 logo
GPT-5.2Advanced Investment Memo (IC Memo)
gpt-5.2 logo
GPT-5.2

1) Recommendation, 12-month PT range, 2-sentence thesis

Recommendation: SHORT LLLT
12-month PT range: $25–$42 (central $30)

Thesis (2 sentences): LLLT is a high-quality mid-market spend/AP SaaS business, but the stock embeds a valuation that requires durable >20% growth and sustained margin expansion well beyond our base-case cash flow trajectory. On our DCF work, intrinsic value clusters materially below the current price ($46), leaving asymmetric downside if NRR normalizes, growth decelerates, or operating leverage arrives slower than expected.


2) Business overview + why it wins / why now

What it does: LedgerLift sells B2B spend management and AP automation software to mid-market enterprises. Revenue is 92% subscription / 8% services, with subscription gross margin around 82% (services GM ~25%).

Why it wins (likely):

  • Sticky workflow + compliance adjacency: AP/spend sits in a “system-of-record” lane; switching costs are real once policies, approvals, and integrations are embedded.
  • Proven land-and-expand motion: NRR 123% with 94% gross retention implies meaningful expansion (modules/seats/volume) even after churn.
  • Unit economics that scale: 18-month CAC payback and 78% FY25 gross margin suggest attractive LTV/CAC if retention holds.

Why now: The setup is valuation-driven. At $46, LLLT’s market pricing appears to discount a continuation of premium SaaS metrics (NRR, margin expansion) despite decelerating growth implied by our 2026–2030 assumptions and the natural maturing of a 6,200-customer base.


3) KPI quality check (and what could be wrong)

NRR (123%) / Gross retention (94%): Strong—supports expansion-led growth.
What could be wrong: NRR can be flattered by (i) price increases, (ii) payment volume-driven modules that are cyclical, or (iii) expansions concentrated in a subset of larger customers; if cohorts mature, NRR can step down quickly.

Logo churn (6%/yr): Reasonable for mid-market; not “best-in-class” for core finance workflows.
What could be wrong: Churn may be understated if downsells are classified as contraction rather than churn; macro pressure in mid-market can raise churn faster than management expects.

CAC payback (18 months) & S&M (34% of rev in FY25): Healthy but not ultra-efficient.
What could be wrong: Payback can deteriorate if growth relies more on new logos vs. expansion; also, payback looks best during periods of strong pipeline conversion.

Customer concentration: Top 10 = 16% of revenue; top 1 = 3% (not alarming).
What could be wrong: Even without headline concentration, expansions may be concentrated—i.e., NRR driven by a narrow slice of the base.


4) Base/Bull/Bear model (2026–2030) + DCF outputs

Model mechanics (all cases):
Unlevered FCF = EBIT(1–tax) + D&A – Capex – ΔNWC

  • Tax: 23% cash tax rate
  • D&A: 2.5% of revenue
  • Capex: 3.0% of revenue
  • NWC investment: 1.0% of incremental revenue
    DCF: PV of 2026–2030 FCF + PV of terminal value (TV = FCF_2030×(1+g)/(WACC–g)).

Forecasts and cash flows ($m)

Base case (WACC 10%, g 3%)

$m20262027202820292030
Revenue9921,1711,3461,5211,704
EBIT198258323380443
Unlevered FCF146191240284331

Bull case (WACC 9%, g 4%)

$m20262027202820292030
Revenue
Advanced Investment Memo (IC Memo)

Turn this model response into notes, narration, or a short video

Auto NotesTranscriptNarrateVideo Cut

Partner link

This output is part of our open dataset — 5K+ AI responses across 200 models

About GPT-5.2

Capabilities

ConversationReasoningCode GenerationAnalysis

Categories

TextCodeMultimodal

Specifications

Provider
Openai
Released
2025-12-10
Size
XLARGE
Context
400,000 tokens

Keep exploring

SAME PROMPT

Claude Sonnet 4.6's version

Same prompt, different result

COMPARE

GPT-5.2 vs Gemini 3.1 Pro Preview

Both outputs, side by side

Compare AI vibes, not scores. Side-by-side outputs across the world's best models.

@rival_tips

Explore

  • Compare Models
  • All Models
  • Leaderboard
  • Challenges

Discover

  • AI Creators
  • AI Tools
  • The Graveyard

Developers

  • Developer Hub
  • MCP Server
  • .llmignore
  • Badges
  • RIVAL Datasets

Connect

  • Methodology
  • Sponsor
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed
© 2026 Rival