Compare top models

LLM Benchmarks

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

← Back

Gemini 3.1 Pro

TypeScript · With Guidelines · 2026-07-14
0.0%Task Pass Rate
0/89Checks Passed
47Total Evals

Pass Rate Over Time

Click a data point to view results from that date.

auth

0% · 8 evals
PassTaskChecksRun Time
✗Auth Identity Check0/112.7s
✗Private Vs Public Table0/113.3s
✗Registered User Gate0/114.8s
✗Admin Bootstrap0/112.7s
✗Role Based Access0/112.7s
✗Ban List0/113.2s
✗Rate Limit0/113.1s
✗Shared Document0/112.8s

basics

0% · 15 evals
PassTaskChecksRun Time
✗Empty Reducers0/112.9s
✗Basic Tables0/18.4s
✗Scheduled Table0/112.2s
✗Struct In Table0/17.8s
✗Insert0/28.2s
✗Update0/312.4s
✗Delete0/311.1s
✗Crud0/411s
✗Index Lookup0/311.7s
✗Init0/410s
✗Connect0/18s
✗Helper Function0/37.4s
✗Schedule At Time0/112.9s
✗Cancel Schedule0/112.8s
✗Lifecycle Player0/19.2s

data modeling

0% · 6 evals
PassTaskChecksRun Time
✗Event Table0/16.7s
✗Optional Fields0/19s
✗Cascade Delete0/110.6s
✗Filter And Aggregate0/111.3s
✗Wo Table Join0/113.1s
✗Unique Constraint0/17.6s

queries

0% · 8 evals
PassTaskChecksRun Time
✗View Basic0/112.6s
✗View Per User0/19s
✗Range Query0/113.6s
✗Sort And Limit0/114.3s
✗Find First0/112.5s
✗Select Distinct0/114.8s
✗Count Without Collect0/114.2s
✗Multi Column Filter0/113.7s

schema

0% · 10 evals
PassTaskChecksRun Time
✗Spacetime Product Type0/332.5s
✗Spacetime Sum Type0/326.1s
✗Elementary Columns0/322.9s
✗Product Type Columns0/325.2s
✗Sum Type Columns0/39.4s
✗Scheduled Columns0/213.1s
✗Constraints0/311.6s
✗Many To Many0/529.5s
✗Ecs0/712.8s
✗Multi Column Index0/58.6s