The Quilty Score
A 0-100 weighted composite that evaluates screenplays, pilot scripts, and stage plays with purpose-built frameworks for each medium.
Three distinct scoring systems — because what makes a great film, a renewable TV series, and a stage-worthy play are fundamentally different questions.
Three Mediums, Three Frameworks
Each Quilty Score is purpose-built for how its medium actually gets evaluated, financed, and produced. Different pillars, different weights, different verdict tiers.
Film
4 Pillars
Temporal-aware scoring for feature screenplays. Evaluates story craft, market viability, cultural resonance, and production feasibility.
Television
5 Pillars
TV-native scoring for pilots, bibles, and series. Evaluates series engine sustainability, ensemble durability, and streaming economics.
Theatre
5 Pillars
Stage-native scoring for plays and musicals. Evaluates theatricality, live audience engagement, and Regional-to-Broadway viability.
Film Quilty Score
The original Quilty Score. A four-pillar, temporal-aware framework that evaluates feature screenplays the way studios actually greenlight films — balancing craft, commerce, culture, and production reality.
The Greenlight Scale
Thresholds calibrated against real screenplay performance data.
Fast-track for production. Exceptional screenplay with outstanding commercial and creative potential.
Recommend for greenlight with standard development notes. Strong screenplay ready to move forward.
Greenlight viable once key notes are addressed. Solid material with clear commercial path.
Has potential but needs further development before greenlight consideration.
Fundamental issues to resolve. Not ready for greenlight consideration.
Major structural and commercial challenges. Consider reconceptualization.
The Four Dimensions
Each dimension captures a different aspect of screenplay potential. Some are timeless, others shift with the cultural moment.
Story & Craft
35%Script-intrinsic quality: structure, character development, dialogue, originality
Good structure in 1980 is good structure in 2025. Universal storytelling principles don't change.
Market Viability
30%Commercial potential: genre heat, market trends, audience demand
Westerns peaked in 1955, niche in 2025. Superhero films peaked in 2010s, declining now.
Culture & Resonance
20%Zeitgeist alignment: thematic relevance, cultural anxieties, social resonance
Cold War anxiety scripts scored high in 1984, low today. Climate anxiety scores high now.
Feasibility
15%Production practicality: budget efficiency, technical complexity, production risk
VFX-heavy scripts scored lower pre-CGI (expensive practicals), higher today (affordable digital).
Why Film Scores Change Over Time
The Film Quilty Score is time-aware. A screenplay scored in 2025 may have a different score if assessed in 1984 or 2040. Here's why:
The Red Dawn Effect
Depreciating IP: Some scripts are tied to their era. Cold War thrillers scored high in 1984 but collapse after 1991.
Red Dawn (1984): Market 79 → 45 (2025)
Same script, different era = different score
The Get Out Effect
Cultural Moment: Scripts that tap into social zeitgeist can surge in relevance when the cultural conversation aligns.
Get Out (2017): Cultural 65 → 89 (post-2017)
Social themes amplified by real-world discourse
The WarGames Effect
Resilient IP: Universal themes transcend era. Technology vs. humanity, unintended consequences — these themes become MORE relevant.
WarGames (1983): Cultural 48 → 55 (2025)
AI/cyber themes more relevant today than ever
Quilty Score Over Time (1986-2025)
How would the same screenplay score if evaluated in different eras? This chart shows 5 top-rated films (one per genre) scored across 40 years.
Note: Story & Craft scores remain constant (good structure is always good structure). Variations come from Market Viability, Cultural Resonance, and Feasibility dimensions which respond to genre cycles, cultural themes, and technology eras.
The Shining (1980)
Budget: $19M
Box Office: $44M
ROI: 2.3x
Critical: 84% RT
The Dark Knight (2008)
Budget: $185M
Box Office: $1B
ROI: 5.4x
Critical: 94% RT
The Shawshank Redemption (1994)
Budget: $25M
Box Office: $58M
ROI: 2.3x
Critical: 91% RT
Se7en (1995)
Budget: $33M
Box Office: $327M
ROI: 9.9x
Critical: 82% RT
Groundhog Day (1993)
Budget: $14M
Box Office: $105M
ROI: 7.5x
Critical: 94% RT
Critic Consensus vs. Quilty — 2016 to 2026
See the 50 most critically loved films of the past decade placed next to their Quilty Scores, with the pillar breakdown that explains every gap.
Temporal Scoring Case Studies
Deep dives into how specific films score across eras, and what that reveals about IP valuation.
Get Out (2017)
Released 2017
Real-World Performance
$4.5M
$255M
56x
98% RT
Awards: Best Original Screenplay (Oscar)
Cultural Impact: Launched Jordan Peele's career, sparked national conversations on race
Analysis
Story & Craft (89.2) validated by Oscar win. Market Viability (82.5) validated by 56x ROI. Cultural score was under-estimated due to semantic matching limitations—the film's perfect 2017 zeitgeist alignment should have been 80+.
Honest caveat
Model under-rated Cultural Resonance at the time of release. Even with the era-locked 2017 score (72), Quilty would have flagged this as worth making — but the magnitude of the cultural moment was outside the model's 2017 reach.
Red Dawn (1984)
Released 1984
Real-World Performance
$17M
$38M
2.2x
52% RT
Cultural Impact: Cold War zeitgeist capture, but themes aged poorly post-1991
Analysis
The "Red Dawn Effect" in action: High market viability in 1984 (Cold War tensions) collapsed after the Soviet Union fell. Same script, different era = different score. A depreciating IP asset.
Honest caveat
Model would have correctly rated this as releasable in 1984. It also correctly identifies the script as a depreciating asset for any modern remake — which is the actionable use of temporal scoring.
WarGames (1983)
Released 1983
Real-World Performance
$12M
$79M
6.6x
93% RT
Cultural Impact: Influenced real cybersecurity policy, themes more relevant today
Analysis
The "WarGames Effect": Universal themes (technology vs. humanity, unintended consequences) transcend era. Score actually increased over time as AI/cyber themes became more relevant. A resilient IP asset.
Honest caveat
A clean win for Quilty in both eras. The 1983 era-locked score correctly anticipates an audience while the 2025 score reflects how the AI/cyber lens has expanded the cultural surface area.
Mad Max: Fury Road (2015)
Released 2015
Real-World Performance
$150M
$380M
2.5x
97% RT
Awards: 6 Oscars (Editing, Costume, Production Design, Makeup, Sound Mixing, Sound Editing)
Cultural Impact: Reframed the legacy-IP-revival template; visual grammar widely imitated 2015-2025.
Analysis
High Story & Craft (91) plus high Cultural (88) is the rare combination Quilty most reliably flags. Market Viability scored conservatively because of the 30-year franchise gap — that conservatism was warranted; the box-office multiple was strong but not blockbuster.
Honest caveat
Quilty would have correctly recommended a green light. It would NOT have predicted the 6-Oscar haul — craft scoring confirms quality but does not forecast Academy voting behavior.
The Blair Witch Project (1999)
Released 1999
Real-World Performance
$60K
$248M
4,133x
86% RT
Cultural Impact: Launched the modern found-footage subgenre and defined viral pre-internet film marketing.
Analysis
A clean miss for the model in 1999. Market Viability scored low (38) because there was no 1999 comp for found-footage horror. The 2025 retrospective score (78) reflects a category Blair Witch itself created — which is exactly the prediction problem novelty creates.
Honest caveat
Honest admission: Quilty would NOT have predicted this outcome. Category-defining films are structurally hard to score because the model relies on comps. We surface this case study so writers see where the model is weakest.
John Carter (2012)
Released 2012
Real-World Performance
$263M
$284M
~0.6x net (after marketing)
52% RT
Cultural Impact: One of the largest single-title write-downs in studio history (~$200M). Cited in textbooks on tentpole risk.
Analysis
Quilty would have flagged this in 2012 with a borderline 61 — Cultural Moment of 42 is the warning shot. The story craft was workmanlike; the spend-vs-cultural-relevance gap is what made this a textbook flop. A $50M version of the same script scores very differently.
Honest caveat
Quilty cannot price-set a project. It can warn that a Cultural Moment under 50 is incompatible with a $250M production budget. The model would have urged a smaller-scale version of the same screenplay.
Cats (2019)
Released 2019
Real-World Performance
$95M
$73M
~0.5x net (after marketing)
20% RT
Cultural Impact: A widely cited example of theatrical-IP-translation risk and VFX timeline pressure.
Analysis
A clean call for the model. Cultural Moment (35) and Story & Craft (52) together fall well below greenlight territory; combined low Feasibility (60, reflecting a high-risk VFX pipeline) compounded the warning. This is the cleanest "Quilty would have said no" example we have.
Honest caveat
A potential overconfidence trap: Quilty rated this conservatively, but the model still cannot tell a studio when a beloved IP is "translation-resistant." Naming that risk is the writer's job; the score is the prompt to ask the question.
Backtests & Honest Caveats
How does Quilty perform against produced films we already know the outcome of?
Curated retrospective validation across hits, sleepers, and flops. Era-locked scores (the score Quilty would have produced at release) are compared to actual market and critical performance. Each row includes an explicit "what Quilty could not have known" admission so you can see where the model is weakest, not just where it is right.
What this is — and is not
- Retrospective validation, not forecasting. Era-locked scores are best-effort reconstructions of how the model would have scored each script at release, controlling for what was knowable at the time.
- Small curated sample. 7 films chosen to include hits, sleepers, and flops so the page is not a victory lap.
- The Quilty Score is a craft + market read, not a guarantee. A high score is a reason to make a film, not a promise that it will hit. A low score is a reason to revise, not proof it will fail.
- Zeitgeist is hard. Category-defining films (see The Blair Witch Project, 1999) are structurally hardest to score — there is no comp by definition.
| Film | Era-locked score | Outcome | Real-world result | Was Quilty right? |
|---|---|---|---|---|
Get Out (2017) 2017 model | 72 | hit | Box office: $255M ROI: 56x Critics: 98% RT | Model under-rated Cultural Resonance at the time of release. Even with the era-locked 2017 score (72), Quilty would have flagged this as worth making — but the magnitude of the cultural moment was outside the model's 2017 reach. |
Red Dawn (1984) 1984 model | 64.3 | mixed | Box office: $38M ROI: 2.2x Critics: 52% RT | Model would have correctly rated this as releasable in 1984. It also correctly identifies the script as a depreciating asset for any modern remake — which is the actionable use of temporal scoring. |
WarGames (1983) 1983 model | 71.5 | hit | Box office: $79M ROI: 6.6x Critics: 93% RT | A clean win for Quilty in both eras. The 1983 era-locked score correctly anticipates an audience while the 2025 score reflects how the AI/cyber lens has expanded the cultural surface area. |
Mad Max: Fury Road (2015) 2015 model | 87.4 | hit | Box office: $380M ROI: 2.5x Critics: 97% RT | Quilty would have correctly recommended a green light. It would NOT have predicted the 6-Oscar haul — craft scoring confirms quality but does not forecast Academy voting behavior. |
The Blair Witch Project (1999) 1999 model | 58 | sleeper | Box office: $248M ROI: 4,133x Critics: 86% RT | Honest admission: Quilty would NOT have predicted this outcome. Category-defining films are structurally hard to score because the model relies on comps. We surface this case study so writers see where the model is weakest. |
John Carter (2012) 2012 model | 61 | flop | Box office: $284M ROI: ~0.6x net (after marketing) Critics: 52% RT | Quilty cannot price-set a project. It can warn that a Cultural Moment under 50 is incompatible with a $250M production budget. The model would have urged a smaller-scale version of the same screenplay. |
Cats (2019) 2019 model | 49.5 | flop | Box office: $73M ROI: ~0.5x net (after marketing) Critics: 20% RT | A potential overconfidence trap: Quilty rated this conservatively, but the model still cannot tell a studio when a beloved IP is "translation-resistant." Naming that risk is the writer's job; the score is the prompt to ask the question. |
Want to suggest a film for the next round of backtests? hello@quilty.app. We are particularly interested in cases where the model would likely have been wrong — those are the most useful for everyone.
TV Quilty Score
Television is a longevity business. The TV Quilty Score is built from the ground up to evaluate what actually drives greenlight, renewal, and cancellation decisions in episodic television — series engine sustainability, ensemble durability, and streaming economics.
TV Verdict Tiers
Calibrated to match the rigor of studio greenlight decisions, from straight-to-series to pass.
Exceptional series engine, high projected efficiency score. Fast-track for production with minimal development.
Strong commercial viability and capable engine. Greenlight with funded development room for tonal balancing.
Promising concept and characters. Series engine needs multi-season sustainability work before committing.
Script functions as closed-loop narrative rather than open-ended series. High subscriber churn risk.
Fundamental structural flaws or unfeasible production demands for episodic television.
The Five Pillars
Each pillar aggregates scores from multiple TV intelligence features. Pillar weights adjust automatically based on series format (ongoing, limited, procedural, anthology).
Series Engine & Craft
30%Pilot craft, chronic conflict renewability, serialization architecture, bible compatibility, multi-season story potential
8 features including pilot evaluation, series engine assessment, episode breakdown, and bible sales readiness
Character & Ensemble
20%Ensemble sustainability, character grid depth, relationship engine, cast resilience across 50+ hours of television
Evaluates whether characters can sustain multi-season arcs without dramatic redundancy
Platform & Market
20%Platform alignment, competitive landscape, target audience, global licensing and IP franchise potential
5 features including competitive landscape analysis and global licensing potential via real-time market data
Cultural Resonance
15%Cultural conversation potential, zeitgeist alignment, binge-worthiness, awards trajectory, marketing hooks
Predicts cultural staying power and whether the series drives subscriber acquisition vs. retention
Production & Business
15%Budget-to-platform alignment, WGA 2023 MBA compliance, casting logistics, renewal economics, rights and compliance risk
7 features including writers room intelligence, casting intelligence, and rights/compliance risk assessment
What Makes the TV Score Different
25 TV Intelligence Features
From pilot evaluation to bible sales readiness, each feature is scored by a purpose-selected AI model (Claude, Grok, Perplexity, Gemini, OpenAI).
Format-Adaptive Weights
Pillar weights shift automatically for limited series (higher cultural resonance), procedurals (higher ensemble weight), and anthologies.
Series Engine Assessment
Evaluates chronic conflict, renewable premise, and whether the pilot creates an open-ended story engine or a closed-loop film narrative.
Streaming Economics
Projects efficiency scores, churn mitigation potential, 60-day demand multipliers, and audience cohort quality against platform economics.
Theatre Quilty Score
Stage plays are not films shot from a fixed seat. The Theatre Quilty Score evaluates what makes material work as live performance — theatricality, speakability, spatial storytelling, and the economics of producing at Regional, Off-Broadway, and Broadway tiers.
Theatre Verdict Tiers
Calibrated to the commercial theatre development pipeline, from exceptional to not ready.
High potential for successful production. Strong consider for immediate development at target tier.
Solid production potential with clear path forward. Consider for development with standard notes.
Good foundation that needs refinement. Consider with development — dramaturgical work recommended.
Significant revision needed before production-ready. Pass with potential for future reconsideration.
Fundamental issues need addressing. Material not yet suitable for production at any tier.
The Five Pillars
Each pillar aggregates scores from the 13 Theatre Intelligence features, evaluated through the lens of live performance rather than cinematic technique.
Theatricality
25%Stage-worthiness and live performance impact. How well the material exploits the unique properties of live theatre.
Evaluates blocking potential, audience-performer connection, spatial storytelling, and staging complexity
Market Viability
25%Regional, Off-Broadway, and Broadway production potential. Where this play fits in the commercial theatre ecosystem.
Assesses market positioning, comparable productions, audience demographics, and IP analysis
Production Feasibility
20%Technical and logistical producibility. Cast size, set changes, special staging, venue adaptability across production tiers.
Evaluates production requirements and budget tiers from regional ($200K) to Broadway ($15M+)
Artistic Merit
20%Character depth, dialogue quality, and dramatic craft evaluated through the lens of live performance.
Speakability, monologue strength, character revelation, and performability rather than cinematic technique
Commercial Potential
10%Revenue projections, awards potential, and licensing revenue across production tiers.
Evaluates Tony eligibility trajectory, regional licensing value, and cast album / adaptation potential
What Makes the Theatre Score Different
Live Performance Native
Every analysis criterion is theatre-native. Speakability over readability. Blocking potential over camera angles. Audience-performer connection over visual spectacle.
Three Production Tiers
Budget and market analysis spans Regional ($200K-$2M), Off-Broadway ($2M-$6M), and Broadway ($15M+) production tiers with distinct viability assessments for each.
Dialogue Engine
A stage-specific dialogue analysis that evaluates performability, monologue strength, character revelation through speech, and the quality of soliloquies and asides.
13 Intelligence Features
From staging complexity and venue adaptability to comparable productions, audience demographics, revenue projections, and awards potential analysis.
Get Your Quilty Score
Upload your screenplay, pilot script, or stage play and receive a comprehensive, medium-specific analysis in minutes. Purpose-built frameworks for film, television, and theatre.