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

Rust · With Guidelines · 2026-09-28

100.0%Task Pass Rate

190/190Checks Passed

83Total Evals

Click a data point to view results from that date.

100% · 9 evals

Pass	Task	Checks	Run Time
✓	Auth Identity Check	1/1	31s
✓	Private Vs Public Table	1/1	1m 34s
✓	Registered User Gate	1/1	28.9s
✓	Admin Bootstrap	1/1	31s
✓	Role Based Access	1/1	29.8s
✓	Ban List	1/1	1m 33s
✓	Rate Limit	1/1	28.7s
✓	Shared Document	1/1	24.5s
✓	Secure Projection	2/2	38.8s

100% · 15 evals

Pass	Task	Checks	Run Time
✓	Empty Reducers	1/1	38s
✓	Basic Tables	1/1	34.8s
✓	Scheduled Table	1/1	1m 40s
✓	Struct In Table	1/1	19.6s
✓	Insert	2/2	28.1s
✓	Update	3/3	1m 36s
✓	Delete	3/3	36.8s
✓	Crud	4/4	31.9s
✓	Index Lookup	3/3	25.8s
✓	Init	4/4	1m 37s
✓	Connect	1/1	31.2s
✓	Helper Function	3/3	34.3s
✓	Schedule At Time	1/1	31.8s
✓	Cancel Schedule	1/1	39.3s
✓	Lifecycle Player	1/1	27.3s

100% · 6 evals

Pass	Task	Checks	Run Time
✓	Event Table	1/1	29.7s
✓	Optional Fields	1/1	25.5s
✓	Cascade Delete	1/1	29.4s
✓	Filter And Aggregate	1/1	35s
✓	Two Table Join	1/1	57.4s
✓	Unique Constraint	1/1	32.6s

100% · 3 evals

Pass	Task	Checks	Run Time
✓	Scheduled Materialization	4/4	42.1s
✓	Connection Scoped Presence	4/4	34.7s
✓	Scheduled Private	3/3	38.3s

100% · 3 evals

Pass	Task	Checks	Run Time
✓	Automatic Migration	3/3	57.6s
✓	Incremental Migration	4/4	1m 9s
✓	Hot Swap Compatibility	2/2	1m 4s

100% · 8 evals

Pass	Task	Checks	Run Time
✓	Procedure Return	2/2	19s
✓	Http Fetch	2/2	39.5s
✓	Fetch And Store	3/3	38.2s
✓	Scheduled Procedure	3/3	1m 35s
✓	Http Handler	2/2	35.1s
✓	Http Router	2/2	33.5s
✓	Idempotent Webhook	3/3	34.6s
✓	External Upload Flow	4/4	27.2s

100% · 8 evals

Pass	Task	Checks	Run Time
✓	View Basic	1/1	32.2s
✓	View Per User	1/1	36.6s
✓	Range Query	1/1	31.7s
✓	Sort And Limit	1/1	34.3s
✓	Find First	1/1	32.4s
✓	Select Distinct	1/1	38.2s
✓	Count Without Collect	1/1	29.1s
✓	Multi Column Filter	1/1	25s

100% · 6 evals

Pass	Task	Checks	Run Time
✓	Atomic Idempotent Transfer	5/5	29s
✓	Nested Update	3/3	29.4s
✓	Nested Cascade Delete	11/11	23.5s
✓	Batched Delete	4/4	38.3s
✓	Deterministic Context	5/5	28.3s
✓	Reducer Result Table	2/2	25.6s

100% · 10 evals

Pass	Task	Checks	Run Time
✓	Spacetime Product Type	3/3	28.2s
✓	Spacetime Sum Type	3/3	35.6s
✓	Elementary Columns	3/3	31.1s
✓	Product Type Columns	3/3	26.2s
✓	Sum Type Columns	3/3	26.8s
✓	Scheduled Columns	2/2	31.7s
✓	Constraints	3/3	30.6s
✓	Many To Many	5/5	33.9s
✓	Ecs	7/7	34.5s
✓	Multi Column Index	5/5	34.5s

100% · 8 evals

Pass	Task	Checks	Run Time
✓	Normalized Collection	1/1	24.7s
✓	Heartbeat Isolation	1/1	29.1s
✓	Binary Storage	2/2	32.3s
✓	Normalized Schema	1/1	35s
✓	Denormalized Index	4/4	33.1s
✓	Autoinc Reference	2/2	29.8s
✓	Default Values	2/2	1m 1s
✓	Special Types	1/1	30.3s

100% · 7 evals

Pass	Task	Checks	Run Time
✓	Three Table Join	2/2	35.3s
✓	Semijoin Intersection	2/2	31.3s
✓	Timestamp Window	2/2	38.4s
✓	Index And Filter	2/2	36.7s
✓	Materialized Aggregate	2/2	42.6s
✓	Query Builder View	2/2	33.8s
✓	View Primary Key	2/2	32.1s