Compare top models

LLM Benchmarks

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

google/gemini-3-flash-preview

Typescript · With Guidelines
97.8%Task Pass Rate
87/89Checks Passed
47Total Evals

Pass Rate Over Time

Click a data point to view results from that date.

auth

100% · 8 evals
StatusTask IDChecksRun Time
t_045_rate_limit1/14m 43s
t_026_auth_identity_check1/14m 54s
t_027_private_vs_public_table1/115.2s
t_041_registered_user_gate1/15m 23s
t_042_admin_bootstrap1/122.5s
t_043_role_based_access1/129.3s
t_044_ban_list1/15m 30s
t_046_shared_document1/16m 5s

basics

97% · 15 evals
StatusTask IDChecksRun Time
t_000_empty_reducers1/111.7s
t_001_basic_tables1/19.1s
t_002_scheduled_table1/15m 29s
t_003_struct_in_table0/110.1s
t_004_insert2/211.9s
t_005_update3/313.3s
t_006_delete3/311.7s
t_007_crud4/413.0s
t_008_index_lookup3/318.8s
t_009_init4/410.1s
t_010_connect1/115.1s
t_011_helper_function3/312.1s
t_038_schedule_at_time1/111.9s
t_039_cancel_schedule1/113.9s
t_040_lifecycle_player1/115.6s

data modeling

100% · 6 evals
StatusTask IDChecksRun Time
t_029_filter_and_aggregate1/122.1s
t_030_two_table_join1/14m 47s
t_024_event_table1/114.4s
t_025_optional_fields1/113.6s
t_028_cascade_delete1/122.1s
t_031_unique_constraint1/114.4s

queries

88% · 8 evals
StatusTask IDChecksRun Time
t_022_view_basic0/114.0s
t_023_view_per_user1/115.7s
t_032_range_query1/126.1s
t_033_sort_and_limit1/14m 50s
t_034_find_first1/118.3s
t_035_select_distinct1/115.1s
t_036_count_without_collect1/134.0s
t_037_multi_column_filter1/122.7s

schema

100% · 10 evals
StatusTask IDChecksRun Time
t_012_spacetime_product_type3/312.5s
t_013_spacetime_sum_type3/311.8s
t_014_elementary_columns3/312.4s
t_015_product_type_columns3/319.7s
t_016_sum_type_columns3/314.4s
t_017_scheduled_columns2/25m 47s
t_018_constraints3/312.8s
t_019_many_to_many5/55m 31s
t_020_ecs7/725.9s
t_021_multi_column_index5/514.4s