Compare top models

LLM Benchmarks

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

← Back

Anthropic: Claude Fable 5.1

Rust · With Guidelines · 2026-09-02
96.6%Task Pass Rate
86/89Checks Passed
47Total Evals

Pass Rate Over Time

Click a data point to view results from that date.

auth

100% · 8 evals
PassTaskChecksRun Time
Auth Identity Check1/114.7s
Private Vs Public Table1/123.9s
Registered User Gate1/119.4s
Admin Bootstrap1/116.2s
Role Based Access1/131.2s
Ban List1/119.8s
Rate Limit1/130.1s
Shared Document1/130.9s

basics

93% · 15 evals
PassTaskChecksRun Time
Empty Reducers1/124.7s
Basic Tables0/126.0s
Scheduled Table1/125.1s
Struct In Table0/121.0s
Insert2/220.4s
Update3/325.1s
Delete3/323.6s
Crud4/425.4s
Index Lookup3/326.9s
Init4/421.0s
Connect1/124.9s
Helper Function3/318.8s
Schedule At Time1/124.9s
Cancel Schedule1/125.2s
Lifecycle Player1/123.6s

data modeling

100% · 6 evals
PassTaskChecksRun Time
Event Table1/131.2s
Optional Fields1/129.8s
Cascade Delete1/131.5s
Filter And Aggregate1/131.4s
Wo Table Join1/132.0s
Unique Constraint1/131.1s

queries

88% · 8 evals
PassTaskChecksRun Time
View Basic1/121.1s
View Per User0/125.1s
Range Query1/122.1s
Sort And Limit1/123.5s
Find First1/125.6s
Select Distinct1/125.1s
Count Without Collect1/122.4s
Multi Column Filter1/124.3s

schema

100% · 10 evals
PassTaskChecksRun Time
Spacetime Product Type3/327.1s
Spacetime Sum Type3/327.5s
Elementary Columns3/327.1s
Product Type Columns3/328.8s
Sum Type Columns3/331.8s
Scheduled Columns2/223.5s
Constraints3/323.2s
Many To Many5/525.9s
Ecs7/726.6s
Multi Column Index5/531.2s