Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedVoxel World
Minecraft-style browser game
CresciBenchPreparing runs
CresciBench Core
See what every model builds under pressure
Compare complete games, apps, landing pages, data products, and defensive security labs by challenge, sector, or model. Versioned evidence keeps capability, reliability, risk, visual quality, latency, and cost separate.
Public evidence contract
The API exposes status for withheld runs, never synthetic model aggregates. A live ranking requires a complete verified release using the clean external core-v2 catalog, explicit approval, and an exact report-and-artifact evidence seal. The 20 public prompts and their canonical repetition-1 responses are disclosed only after that gate; there is no reserved payload-membership index. Private payloads, full artifacts, and tool traces remain outside Git and Vercel.
Core report JSONEvidence explorer
See what every model builds under pressure
Compare one-attempt games, product interfaces, landing pages, data products, and defensive security labs. Every output is judged against the same published stress contract; empty cards are explicit run slots, never simulated results.
- Models
- 11
- Stress tests
- 36
- Output slots
- 396
- Published
- 0
- One attempt
- 12k token cap
- Offline artifact
- Responsive
- Failure states
- 100-point rubric
Core release: emptyOpen official leaderboard
OpenAI
GPT-5.6 Sol
openai/gpt-5.6-sol · openrouter
- Input
- $5/ 1M
- Output
- $30/ 1M
textreasoningcodevisiontool-use
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
high stress
Run not startedOrbital Runner
Fast arcade challenge with a complete score loop
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedTactical Grid Arena
Turn-based tactics against a deterministic local opponent
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedPhysics Puzzle Lab
Multi-level construction puzzle with undo and recovery
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedCity Builder Sandbox
Resource simulation with placement, trade-offs, and recovery
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
high stress
Run not startedRhythm Signal
Audio-optional timing game with visual cues and calibration
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedSupport Command Center
Agent workspace for triaging customer conversations
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
high stress
Run not startedField Service Planner
Scheduling workspace for mobile operations teams
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedCollaborative Roadmap
Product planning workspace with dependencies and conflicts
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedInventory Operations
Warehouse workspace for stock, replenishment, and anomalies
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedFinance Close Workspace
Month-end close with approvals, exceptions, and audit evidence
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedTravel Disruption Desk
Rebooking operations under capacity and policy constraints
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
high stress
Run not startedAlpine Studio
Editorial portfolio for a mountain architecture practice
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedSaaS Conversion Lab
Conversion-focused landing page for an AI workflow platform
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
high stress
Run not startedLuxury Property Launch
Editorial launch page for a high-end coastal residence
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedHealthcare Trust Landing
Patient-first landing page for a digital care service
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedDeveloper Platform Launch
Technical launch page for an API and automation platform
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedClimate Tech Launch
Credible industrial decarbonization landing page
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
high stress
Run not startedNight Market Identity
Campaign system for a city food and culture festival
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
high stress
Run not startedKinetic Product Launch
Visual launch kit for a performance footwear release
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
high stress
Run not startedAlbum Release System
Music launch identity across cover, social, and release moments
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedMuseum Exhibition Identity
Cultural identity across exhibition, wayfinding, and ticketing
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedSustainable Beauty Campaign
Premium product system with disciplined claim boundaries
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedEsports Tournament Package
Broadcast-ready identity for a competitive event
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedUrban Mobility Pulse
Interactive dashboard for city transport performance
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedRevenue Forecast Studio
SaaS scenario planning with assumptions and uncertainty
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedSupply Chain Risk Map
Supplier and geography risk exploration without external maps
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedClinical Operations Monitor
Privacy-aware hospital operations dashboard using synthetic data
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedEnergy Grid Control Room
Synthetic grid performance, forecast, and alert triage
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedExperimentation Analysis Lab
A/B analysis with sample size, uncertainty, and guardrails
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedSecure Checkout Review
Defensive review of a checkout flow with prioritized remediation
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedPhishing Triage Lab
Evidence-led triage of suspicious messages and indicators
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedIncident Response Console
Defender workspace for triage, containment, and recovery decisions
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedAccess Control Policy Lab
Least-privilege review across roles, resources, and edge cases
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedCloud Misconfiguration Review
Defensive review of synthetic cloud configuration and exposure
Output slot
GPT-5.6 Sol
No generated artifact is being simulated
extreme stress
Run not startedDependency Risk Triage
Defensive SBOM and vulnerability prioritization workspace
Three surfaces, three different questions
Keeping the tracks separate prevents a polished interface from masking weak reasoning, unsafe actions, or unreliable task execution.
Core
Model-only tasks with deterministic checks wherever possible. The capability score excludes agent execution. JavaScript checks require explicit use of a disposable, network-denied Docker sandbox; they never execute inside the application process.
Agent
Tool use and recovery through bounded, read-only virtual tools and explicit budgets. Agent score and reliable agent success are reported separately.
Design
Screenshots and generated interfaces are scored separately against a visual rubric. Design never contributes to Core and remains unranked until a live, rubric-scored release exists.
Open the Design suiteClean external release contract
The clean core-v2 secret pack and public commitments are prepared, but no live ranking has been run. Release still needs provider credentials, a candidate and two independent judge models, a finite approved worst-case budget, the complete 96-task run, verification, and an exact approval evidence seal. Synthetic reports validate only the pipeline and never establish a ranking.
- Public disclosure
- 20 complete public tasks; the 76 exposed reserved tasks are compromised, synthetic/dev-only, and never eligible for a live release.
- Public result gate
- Live, complete, publishable, explicitly approved, and exact report plus artifact-evidence match.
- Code execution
- Explicit opt-in only: digest-pinned, network-denied Docker containers enforce CPU, memory, process, time, output, and filesystem limits with no host mounts.
- Bounded I/O
- Provider bodies cap at 8 MiB. Attachments and artifacts require explicit canonical roots, realpath containment, size checks, and no symlinks.
Results by section
Choose a capability to compare models, then inspect canonical public task responses. Agent and Design remain separate from Overall Core.
Equal scores share the same rank.
Overall Core
Weighted capability across the seven model-only tracks. Agent and Design remain separate.
Awaiting live release
Rankings, model names, winners, and responses remain hidden until a complete live release passes publication, approval, and integrity checks. You can still explore every section above without synthetic results being presented as a model comparison.