Compare top models

LLM Benchmarks

See how today's leading models write Spacetime code, scored task by task on live modules.

OpenAI: GPT-6 Astra

TypeScript · With Guidelines · 2026-11-05
100.0%Task Pass Rate
251/251Checks Passed
96Total Evals

Pass Rate Over Time

Click a data point to view results from that date.

advanced

100% · 12 evals
PassTaskChecksRun Time
✓Atomic Reservation2/27.9s
✓Stable Pagination2/27.5s
✓Online Backfill2/217.9s
✓Incremental Totals2/213.3s
✓Webhook Ordering2/214.3s
✓Lease Fencing2/210.3s
✓Cancel Reschedule2/226.2s
✓Transactional Quota2/26.1s
✓Scheduled Queue2/212.8s
✓Procedure Cache2/214.2s
✓Permission Revocation2/29.5s
✓Multi Session Presence2/211.6s

auth

100% · 9 evals
PassTaskChecksRun Time
✓Auth Identity Check2/24.5s
✓Private Vs Public Table2/24.1s
✓Registered User Gate2/24.9s
✓Admin Bootstrap2/24.6s
✓Role Based Access2/26s
✓Ban List2/26.2s
✓Rate Limit2/25.8s
✓Shared Document2/26.5s
✓Secure Projection3/35.2s

basics

100% · 15 evals
PassTaskChecksRun Time
✓Empty Reducers1/14.5s
✓Basic Tables1/14s
✓Scheduled Table2/211.5s
✓Struct In Table1/13.8s
✓Insert2/23.8s
✓Update3/35.1s
✓Delete4/44.9s
✓Crud4/45.3s
✓Index Lookup3/35.1s
✓Init4/44.9s
✓Connect2/23.9s
✓Helper Function3/34.3s
✓Schedule At Time2/26.4s
✓Cancel Schedule2/25s
✓Lifecycle Player2/23.6s

data modeling

100% · 6 evals
PassTaskChecksRun Time
✓Event Table2/24.5s
✓Optional Fields2/24.9s
✓Cascade Delete2/24.9s
✓Filter And Aggregate2/25.6s
✓Two Table Join2/26.6s
✓Unique Constraint2/24.5s

lifecycle

100% · 3 evals
PassTaskChecksRun Time
✓Scheduled Materialization4/48.8s
✓Connection Scoped Presence5/56.3s
✓Scheduled Private3/39.7s

migrations

100% · 3 evals
PassTaskChecksRun Time
✓Automatic Migration3/36.9s
✓Incremental Migration4/49s
✓Hot Swap Compatibility2/26.8s

procedures

100% · 8 evals
PassTaskChecksRun Time
✓Procedure Return2/23.8s
✓Http Fetch2/25.4s
✓Fetch And Store3/35.5s
✓Scheduled Procedure3/37.6s
✓Http Handler2/23.5s
✓Http Router3/35.1s
✓Idempotent Webhook4/49.4s
✓External Upload Flow4/47.3s

queries

100% · 8 evals
PassTaskChecksRun Time
✓View Basic2/24.8s
✓View Per User2/23.9s
✓Range Query2/24.4s
✓Sort And Limit2/25.9s
✓Find First2/24.9s
✓Select Distinct2/26.2s
✓Count Without Collect2/25.4s
✓Multi Column Filter2/26.1s

reducers

100% · 7 evals
PassTaskChecksRun Time
✓Atomic Idempotent Transfer6/69.1s
✓Nested Update3/35.4s
✓Nested Cascade Delete11/117.1s
✓Batched Delete5/513.2s
✓Deterministic Context5/54.4s
✓Reducer Result Table2/24.8s
✓Caller Error Message2/24.6s

schema

100% · 10 evals
PassTaskChecksRun Time
✓Spacetime Product Type3/34.7s
✓Spacetime Sum Type3/34.7s
✓Elementary Columns3/35.1s
✓Product Type Columns3/35.3s
✓Sum Type Columns3/34.6s
✓Scheduled Columns2/28.8s
✓Constraints3/35s
✓Many To Many5/59.7s
✓Ecs7/712s
✓Multi Column Index5/55.2s

tables

100% · 8 evals
PassTaskChecksRun Time
✓Normalized Collection1/13.9s
✓Heartbeat Isolation1/15.4s
✓Binary Storage2/25.4s
✓Normalized Schema1/15.7s
✓Denormalized Index4/47.3s
✓Autoinc Reference2/25s
✓Default Values2/25.8s
✓Special Types1/15.7s

views

100% · 7 evals
PassTaskChecksRun Time
✓Three Table Join2/29.6s
✓Semijoin Intersection2/25.8s
✓Timestamp Window2/26.1s
✓Index And Filter2/24.9s
✓Materialized Aggregate3/322.6s
✓Query Builder View2/26.3s
✓View Primary Key2/26.1s