Compare top models

LLM Benchmarks

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

openai/gpt-5.6-terra

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_027_private_vs_public_table1/15.4s
t_026_auth_identity_check1/15.9s
t_041_registered_user_gate1/15.2s
t_042_admin_bootstrap1/14.7s
t_043_role_based_access1/15.4s
t_044_ban_list1/18.2s
t_045_rate_limit1/15.2s
t_046_shared_document1/18.3s

basics

93% · 15 evals
StatusTask IDChecksRun Time
t_010_connect1/17.4s
t_000_empty_reducers1/14.6s
t_001_basic_tables1/12.9s
t_002_scheduled_table1/14.1s
t_003_struct_in_table0/13.3s
t_004_insert2/24.2s
t_005_update3/35.2s
t_006_delete3/36.0s
t_007_crud4/47.0s
t_008_index_lookup3/35.1s
t_009_init4/43.7s
t_011_helper_function3/34.0s
t_038_schedule_at_time0/17.7s
t_039_cancel_schedule1/12.8s
t_040_lifecycle_player1/12.3s

data modeling

100% · 6 evals
StatusTask IDChecksRun Time
t_024_event_table1/14.3s
t_025_optional_fields1/14.3s
t_028_cascade_delete1/14.3s
t_029_filter_and_aggregate1/15.6s
t_030_two_table_join1/14.0s
t_031_unique_constraint1/14.3s

queries

100% · 8 evals
StatusTask IDChecksRun Time
t_022_view_basic1/13.3s
t_023_view_per_user1/12.8s
t_032_range_query1/14.0s
t_033_sort_and_limit1/14.0s
t_034_find_first1/13.7s
t_035_select_distinct1/12.7s
t_036_count_without_collect1/14.0s
t_037_multi_column_filter1/13.4s

schema

100% · 10 evals
StatusTask IDChecksRun Time
t_012_spacetime_product_type3/34.7s
t_013_spacetime_sum_type3/34.1s
t_014_elementary_columns3/34.3s
t_015_product_type_columns3/34.3s
t_016_sum_type_columns3/35.7s
t_017_scheduled_columns2/25.5s
t_018_constraints3/33.6s
t_019_many_to_many5/54.7s
t_020_ecs7/79.4s
t_021_multi_column_index5/54.2s