Open scorecard
invest-like.com publishes two scorecards on one page. Section 1 covers the 7 deterministic framework filters (Buffett-Fit, Graham, Lynch, Greenblatt, Munger, Fisher, T. Smith) - rule-based, reproducible from open source, applied to every real operating equity in the coverage universe (~2,800-3,300 stocks after the size and instrument-type filters; live counts shown below). Section 2 covers the LLM-generated Buffett Brain verdicts - smaller cohort, grows over time as invest-like.com caches new verdicts. invest-like.com publishes all the numbers including the misses.
Rule-based scorecard
Buffett-Fit, Graham, Lynch, Greenblatt, Munger, Fisher, and T. Smith - every grade reproducible from open-source rule cascades. No LLM calls in this section. The headline number below comes straight from this engine.
Rule-based · 5-year backtest
Over a rolling 5-year window, stocks that all 7 frameworks rate at B+ or better returned
That is an outperformance of
over the S&P 500, as of 2026-05-24.
Headline cohort: 47 stocks - only 1.5% of the 3,085-stock universe clear the all 7-frameworks bar (every framework scores the company B+ or better). 85% of them were positive over 5 years. Per-stock returns capped at +400%/-100% so single moonshots don't dominate cohort medians - full methodology at the bottom of the page. Fixed snapshot as of 2026-05-24.
Backed by 7 deterministic frameworks
We track 21,000+ stocks across 68 countries and 33 exchanges (roughly half listed outside the US) in the database (search, verdicts, extension). The track-record backtest filters to 10,165 real operating equities with market cap ≥ $500M and full fundamentals - so the grades + returns reflect genuine business quality, not ETF/fund/bond-fund noise. Non-equity instruments (ETFs, REITs, preferreds, bond funds, insurance conglomerates) and tickers under $500M are deliberately excluded from this backtest because Buffett-style rules don't apply cleanly to them.
Conviction Portfolio · top 30 by composite score
Greenblatt-style fixed-size portfolio: highest composite score across all 7 frameworks, capped at 9 stocks per GICS sector so the basket can’t collapse into a single-sector ETF. Equal-weighted. Look-back snapshot, not a forward-tracked portfolio - the Live Model Portfolio further down has no look-back bias but only weeks of history; this surface has 5 years of price data behind today’s rankings.
Equal-weighted basket of the 30 stocks scoring highest across all 7 frameworks (Buffett, Graham, Lynch, Greenblatt, Munger, Fisher, T. Smith), with a 9-per-sector cap so the basket can't collapse into a single-sector ETF.
Look-back snapshot: holds today's top 30 across the full 5y window (no rebalancing in the historical curve). The forward-tracked Live Model Portfolio below has no look-back bias but only weeks of history. Median (not mean) shown to avoid a single blowup or moonshot distorting the comparison.
Halal Conviction Portfolio · top 30 Shariah-compliant
Same top-30 sector-capped algorithm as the standard Conviction Portfolio, applied only to stocks that pass the AAOIFI Shariah screen: no conventional banks, insurance, alcohol, tobacco, gambling, mortgage REITs, or interest-bearing instruments; long-term debt below 30% of market cap. Methodology details in /methodology.
Equal-weighted basket of the 30 stocks scoring highest across all 7 frameworks (Buffett, Graham, Lynch, Greenblatt, Munger, Fisher, T. Smith), with a 9-per-sector cap so the basket can't collapse into a single-sector ETF.
Look-back snapshot: holds today's top 30 across the full 5y window (no rebalancing in the historical curve). The forward-tracked Live Model Portfolio below has no look-back bias but only weeks of history. Median (not mean) shown to avoid a single blowup or moonshot distorting the comparison.
Median basket of every stock where 7 of 7 frameworks currently agree, vs SPY. Both indexed to 0% at t-5y. This tier was auto-picked because it has the strongest 5y median.
44 stocks in the 7/7 cohort, median of cohort returns at each breakpoint. Drag across the chart to read historical values. Survivorship + look-ahead bias disclosed at the top of the page; the chart inherits both.
Same 5y window, broken out by how many frameworks agreed. Median of cohort returns at each breakpoint - endpoints match the tables exactly. More agreement = bigger outperformance, generally. (Lines crossing in tiny cohorts like 7/7 with one stock are small-sample artifacts.)
Each line is the cumulative cohort "at least N frameworks agree." Tighter filters (5+/7, 6+/7) typically pull above wider ones - the gradient is the "selectivity buys outperformance" story made visual.
Same data as above, but cumulative: each row is the cohort where AT LEAST that many frameworks rated the stock a buy. Use this to decide which tier to filter on - tighter tiers (6+/7, 7/7) have fewer stocks but typically higher returns.
| Tier | Stocks | Med 1y | Med 3y | Med 5y | % pos 1y | View |
|---|---|---|---|---|---|---|
| 7/7 | 44 | +8.1% | +79.7% | +105.7% | 66% | View |
| 6+/7 | 80 | +13.6% | +77.0% |
Stocks bucketed by the percentage of Buffett's 14-rule checklist they currently pass. Higher grade = passes more of the documented criteria AND no deal-breakers (negative ROIC, EPS collapse, debt extremes) fired. A+ is reserved for stocks that pass at least 90% of the rules cleanly; commodity producers and REITs are capped at A.
| Grade | Stocks | Med 1y | Med 3y | Med 5y | % pos 1y |
|---|---|---|---|---|---|
| A+ | 14 | -13.9% | +17.7% | +19.6% | 43% |
| A | 71 | +3.4% | +50.8% | +70.7% | 55% |
| B | 135 | +4.3% | +53.0% |
backtest.tsas of the v20 cohort redefinition (2026-05-21). Earlier versions used verdict = "yes", which produced statistically meaningless cohorts of 4 stocks; the threshold-based rule gives real-portfolio sample sizes defensible against the S&P 500.The cross-framework consensus that produces the best-of-7 cohort is documented in a peer-reviewable working paper with a permanent DOI: Cross-Framework Consensus Scoring System for US-Listed Equities (DOI 10.5281/zenodo.20393518, SSRN 6831462). See /papers/ for the full methodology, citation-ready abstract, and both PDF + JSON-LD downloads.
Live model portfolio · forward tracking
A locked-in basket of 30 stocks our rule-based scoring engine flagged as quality compounders on day one. Equal-weight. Same composition until the next rebalance. Updated daily.
v1 seed (2026-05-19): top 30 large caps (market cap >= $5B) by quality_score (>= 55, top decile) with balance sheet net_debt_to_ebitda <= 3. Future generations will use full 7-framework consensus from lib/scoring/.
live_portfolio_picks table's INSERT timestamps.AI scorecard
Each verdict is generated by an LLM (Anthropic / OpenAI). Real money per run, so we cache aggressively and only score the universe we can afford to keep fresh. The cohort grows every week.
Verdicts tracked
661
Tracking since
Jun 2, 2026
A vs D return spread
+9.4%
Avg return of Grade A+/A verdicts minus Grade D. Over weeks of tape this is mostly noise, not signal - a value strategy is judged over years. Shown for transparency, not as proof of an edge.
Early data
636 scored verdicts across all grades, oldest 97 days. Verdicts younger than 7 days are excluded. Cohort-level averages stabilize over months, not weeks - read these numbers as a directional signal, not a proven edge.
Each row is a grade tier on invest-like.com: how many verdicts the platform has issued, how many are old enough to score, the mean and median return, and the share that ended up positive.
| Grade | Total | Avg return | % positive | ||
|---|---|---|---|---|---|
| A+ | 9 | 9 | -0.0% | +0.0% | 56% |
| A | 113 | 109 | +0.1% | +0.1% | 64% |
| B |
Top 5 highest-return verdicts across all grades - actual individual outcomes.
Bottom 5 lowest-return verdicts. Published here on purpose.
The 10 most recent Buffett Brain analyses across all grades.
Each verdict goes through five pillars - moat, durability, management, valuation, financial health - grounded in the actual Berkshire letters.
The Weekly Letter
The same logic that scores the verdicts on this page, applied to a fresh ticker each week. Pulled from current data. One-click unsubscribe.
The 7-framework composite is the average score across whichever of the 7 scorers ran for each stock. Bulls = frameworks rating the stock B+ or better (score ≥ 60).
Methodology: rank candidates by composite framework score (sum of all 7 normalised framework scores), require ≥5y of price history, sector-cap at 9 stocks per GICS sector, fill until basket = 30 stocks. Per-stock returns winsorized at +400%/-100% to prevent moonshots from dominating cohort medians. Refreshed at most daily (the underlying scoring cron runs nightly; the page caches the computed basket for up to 24 hours). Sign in to see ticker names.
The 7-framework composite is the average score across whichever of the 7 scorers ran for each stock. Bulls = frameworks rating the stock B+ or better (score ≥ 60).
Methodology: rank candidates by composite framework score (sum of all 7 normalised framework scores), require ≥5y of price history, sector-cap at 9 stocks per GICS sector, fill until basket = 30 stocks. Per-stock returns winsorized at +400%/-100% to prevent moonshots from dominating cohort medians. Refreshed at most daily (the underlying scoring cron runs nightly; the page caches the computed basket for up to 24 hours). Sign in to see ticker names.
Bucketed by the EXACT number of frameworks (Buffett, Graham, Lynch, Greenblatt, Munger, Fisher, T. Smith) that currently rate the stock as a buy. The cumulative view below answers "X or more".
| Bulls | Stocks | Med 1y | Med 3y | Med 5y | % pos 1y | View |
|---|---|---|---|---|---|---|
| 7/7 | 44 | +8.1% | +79.7% | +105.7% | 66% | View |
| 6/7 | 36 | +15.3% | +62.3% | +97.1% | 61% | View |
| 5/7 | 54 | +8.1% | +40.2% | +48.9% | 59% | View |
| 4/7 | 66 | +7.2% | +58.1% | +65.8% | 67% | View |
| 3/7 | 69 | +4.8% | +50.1% | +54.9% | 58% | View |
| 2/7 | 112 | +14.3% | +66.0% | +49.8% | 62% | View |
| 1/7 | 525 | +10.4% | +47.1% | +39.3% | 62% | View |
| 0/7 | 1,112 | +15.2% | +32.1% | +5.2% | 69% | - |
Median 5y is the most reliable consensus-quality signal - it's the timeframe where multi-framework agreement starts compounding into real outperformance. Tiny buckets (1-2 stocks like the 7/7 row) are shown for transparency but represent a sample too small to generalise from. For the "X or more" view (which tier should I actually filter on?), see the cumulative table below.
| +104.5% |
| 64% |
| View |
| 5+/7 | 134 | +9.2% | +57.2% | +79.8% | 62% | View |
| 4+/7 | 200 | +8.9% | +57.6% | +73.3% | 64% | View |
| 3+/7 | 269 | +8.2% | +53.7% | +69.1% | 62% | View |
| 2+/7 | 381 | +9.6% | +55.7% | +65.8% | 62% | View |
| 1+/7 | 906 | +10.0% | +51.7% | +50.3% | 62% | View |
The 7/7 tier shows just the stocks where every framework agrees - tiniest cohort, highest conviction. Tighter tiers (6+/7, 7/7) have fewer stocks but typically stronger conviction; wider tiers (1+/7, 2+/7) have more stocks but weaker signal. Click any row to see the stocks in that tier - you decide which cohort is right for your style.
| +72.1% |
| 57% |
| C | 248 | +13.9% | +58.7% | +56.2% | 70% |
| D | 548 | +12.2% | +44.4% | +27.9% | 67% |
| F | 1,002 | +17.2% | +30.3% | -2.8% | 66% |
Median is the typical stock's return (outlier-immune). 5y is the timeframe where fundamental scoring historically has an edge - shorter windows (1y / 3y) are dominated by regime effects (junk-rally cycles, sector rotation, multiple expansion / contraction phases). 2025-2026 has been an unusual junk-rally window for quality scoring.
The 10 best-performing stocks currently grading A or A+ on Buffett-Fit. Each row is a stock our deterministic scoring engine flags as a quality compounder today.
Look-back caveat. This table sorts today's A-graders by realized 1y price return. It does NOT mean Buffett-Fit predicted these moves a year ago - the grade is current. Survivorship is real (delisted/bankrupted names aren't shown). Read as "here's what the rule today rewards," not "here's what the rule picked a year ago and got right."
| - |
| $1086.00 |
| $932.26 |
| -14.2% |
| - | $122.78 | $156.29 | +27.3% |
| - | $284.72 | $307.65 | +8.1% |
| - | $534.30 | $535.38 | +0.2% |
| - | $225.32 | $230.36 | +2.2% |
| - | $70.93 | $110.19 | +55.4% |
| - | $43.41 | $49.60 | +14.3% |
| - | $141.97 | $193.78 | +36.5% |
| - | $436.62 | $454.71 | +4.1% |
| - | $322.99 | $409.95 | +26.9% |
| - | $52.98 | $35.86 | -32.3% |
| - | $168.31 | $200.47 | +19.1% |
| - | $67.70 | $78.94 | +16.6% |
| - | $110.94 | $106.20 | -4.3% |
| - | $93.56 | $85.81 | -8.3% |
| - | $245.35 | $262.11 | +6.8% |
| - | $87.09 | $43.82 | -49.7% |
| - | $247.60 | $266.51 | +7.6% |
| - | $38.25 | $34.36 | -10.2% |
| - | $325.72 | $375.07 | +15.2% |
| - | $501.00 | $320.56 | -36.0% |
| - | $91.46 | $96.88 | +5.9% |
| - | $236.34 | $217.90 | -7.8% |
| - | $87.00 | $92.62 | +6.5% |
| - | $385.17 | $362.42 | -5.9% |
| - | $347.24 | $292.70 | -15.7% |
| - | $403.15 | $443.51 | +10.0% |
| - | $299.72 | $373.17 | +24.5% |
| 194 |
| 187 |
| +0.0% |
| +0.0% |
| 58% |
| C | 206 | 199 | +0.0% | +0.0% | 60% |
| D | 139 | 132 | -0.0% | -0.0% | 42% |
| D |
| 27/100 |
| +53.1% |
| 86d |
Jun 15, 2026 | A | 82/100 | +51.9% | 84d |
Jul 1, 2026 | C | 41/100 | +50.4% | 68d |
Jun 13, 2026 | A | 79/100 | +44.7% | 86d |
| A+ |
| 86/100 |
| -56.4% |
| 85d |
Jun 10, 2026 | D | 32/100 | -49.7% | 89d |
Jun 2, 2026 | D | 32/100 | -48.6% | 97d |
Jun 2, 2026 | B | 61/100 | -47.1% | 97d |
| A |
| 76/100 |
| Awaiting price history |
| 2d |
Sep 5, 2026 | B | 66/100 | Awaiting price history | 2d |
Sep 5, 2026 | A | 76/100 | Awaiting price history | 2d |
Sep 4, 2026 | D | 36/100 | Awaiting price history | 3d |
Sep 4, 2026 | A | 70/100 | Awaiting price history | 3d |
Sep 3, 2026 | C | 46/100 | Awaiting price history | 4d |
Sep 3, 2026 | B | 64/100 | Awaiting price history | 4d |
Sep 3, 2026 | D | 39/100 | Awaiting price history | 4d |
Sep 3, 2026 | B | 61/100 | Awaiting price history | 4d |