Compare top models

LLM Benchmarks

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

← Back

Anthropic: Claude Sonnet 5.5

TypeScript · With Guidelines · 2026-11-05
99.2%Task Pass Rate
249/251Checks Passed
96Total Evals

advanced

100% · 12 evals
PassTaskChecksRun Time
✓Atomic Reservation2/26.9s
✓Stable Pagination2/27.1s
✓Online Backfill2/29.4s
✓Incremental Totals2/26.6s
✓Webhook Ordering2/26.3s
✓Lease Fencing2/27.2s
✓Cancel Reschedule2/217.6s
✓Transactional Quota2/24.6s
✓Scheduled Queue2/26.2s
✓Procedure Cache2/26.8s
✓Permission Revocation2/26.6s
✓Multi Session Presence2/24.8s

auth

100% · 9 evals
PassTaskChecksRun Time
✓Auth Identity Check2/24.5s
✓Private Vs Public Table2/23.5s
✓Registered User Gate2/25.1s
✓Admin Bootstrap2/24.7s
✓Role Based Access2/26.2s
✓Ban List2/25.9s
✓Rate Limit2/25.6s
✓Shared Document2/26.6s
✓Secure Projection3/34s

basics

100% · 15 evals
PassTaskChecksRun Time
✓Empty Reducers1/13.8s
✓Basic Tables1/12.9s
✓Scheduled Table2/23.8s
✓Struct In Table1/12.7s
✓Insert2/23.2s
✓Update3/34.1s
✓Delete4/44.1s
✓Crud4/43.7s
✓Index Lookup3/34.2s
✓Init4/43.2s
✓Connect2/23.2s
✓Helper Function3/33.3s
✓Schedule At Time2/23.8s
✓Cancel Schedule2/23.9s
✓Lifecycle Player2/23.2s

data modeling

100% · 6 evals
PassTaskChecksRun Time
✓Event Table2/23.2s
✓Optional Fields2/23.7s
✓Cascade Delete2/23.9s
✓Filter And Aggregate2/24.5s
✓Two Table Join2/23.8s
✓Unique Constraint2/23s

lifecycle

100% · 3 evals
PassTaskChecksRun Time
✓Scheduled Materialization4/45.3s
✓Connection Scoped Presence5/55s
✓Scheduled Private3/35.1s

migrations

100% · 3 evals
PassTaskChecksRun Time
✓Automatic Migration3/35.8s
✓Incremental Migration4/47.5s
✓Hot Swap Compatibility2/26.2s

procedures

100% · 8 evals
PassTaskChecksRun Time
✓Procedure Return2/23s
✓Http Fetch2/24s
✓Fetch And Store3/34s
✓Scheduled Procedure3/34.7s
✓Http Handler2/23.4s
✓Http Router3/33.1s
✓Idempotent Webhook4/46s
✓External Upload Flow4/44.7s

queries

100% · 8 evals
PassTaskChecksRun Time
✓View Basic2/23.2s
✓View Per User2/23s
✓Range Query2/24s
✓Sort And Limit2/24.2s
✓Find First2/23.3s
✓Select Distinct2/23.6s
✓Count Without Collect2/24s
✓Multi Column Filter2/23.9s

reducers

100% · 7 evals
PassTaskChecksRun Time
✓Atomic Idempotent Transfer6/66.3s
✓Nested Update3/34.4s
✓Nested Cascade Delete11/115.9s
✓Batched Delete5/56.4s
✓Deterministic Context5/54s
✓Reducer Result Table2/23.2s
✓Caller Error Message2/22.9s

schema

100% · 10 evals
PassTaskChecksRun Time
✓Spacetime Product Type3/33.1s
✓Spacetime Sum Type3/34.1s
✓Elementary Columns3/34.2s
✓Product Type Columns3/34.3s
✓Sum Type Columns3/34s
✓Scheduled Columns2/23.6s
✓Constraints3/33.7s
✓Many To Many5/55.1s
✓Ecs7/75.9s
✓Multi Column Index5/54.3s

tables

100% · 8 evals
PassTaskChecksRun Time
✓Normalized Collection1/12.8s
✓Heartbeat Isolation1/13.9s
✓Binary Storage2/25.1s
✓Normalized Schema1/14.1s
✓Denormalized Index4/46.3s
✓Autoinc Reference2/24.1s
✓Default Values2/25.4s
✓Special Types1/13.2s

views

87% · 7 evals
PassTaskChecksRun Time
✗Three Table Join0/24.9s
✓Semijoin Intersection2/24s
✓Timestamp Window2/24.6s
✓Index And Filter2/23.9s
✓Materialized Aggregate3/37.4s
✓Query Builder View2/23.6s
✓View Primary Key2/23.7s