LLM Benchmark

Detailed Eval Results

How well do leading LLMs write SpacetimeDB code? We prompt each model, run the generated code against live modules, and score with automated checks.

GPT-5.4-mini

Typescript · With Guidelines
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
StatusTask IDChecksRun Time
t_026_auth_identity_check0/14.8s
t_027_private_vs_public_table0/14.9s
t_041_registered_user_gate0/14.1s
t_042_admin_bootstrap0/15.3s
t_043_role_based_access0/16.5s
t_044_ban_list0/16.5s
t_045_rate_limit0/15.3s
t_046_shared_document0/16.3s

basics

0% · 15 evals
StatusTask IDChecksRun Time
t_000_empty_reducers0/13.8s
t_001_basic_tables0/15.0s
t_002_scheduled_table0/14.9s
t_003_struct_in_table0/15.8s
t_004_insert0/25.6s
t_005_update0/36.1s
t_006_delete0/35.5s
t_007_crud0/44.3s
t_008_index_lookup0/37.2s
t_009_init0/45.9s
t_010_connect0/13.3s
t_011_helper_function0/35.1s
t_038_schedule_at_time0/13.3s
t_039_cancel_schedule0/14.6s
t_040_lifecycle_player0/14.4s

data modeling

0% · 6 evals
StatusTask IDChecksRun Time
t_024_event_table0/13.3s
t_025_optional_fields0/12.6s
t_028_cascade_delete0/13.4s
t_029_filter_and_aggregate0/13.4s
t_030_two_table_join0/13.6s
t_031_unique_constraint0/12.6s

queries

0% · 8 evals
StatusTask IDChecksRun Time
t_023_view_per_user0/13.9s
t_022_view_basic0/12.9s
t_032_range_query0/14.1s
t_033_sort_and_limit0/15.6s
t_034_find_first0/14.1s
t_035_select_distinct0/14.1s
t_036_count_without_collect0/14.4s
t_037_multi_column_filter0/14.9s

schema

0% · 10 evals
StatusTask IDChecksRun Time
t_012_spacetime_product_type0/34.8s
t_013_spacetime_sum_type0/35.1s
t_014_elementary_columns0/34.7s
t_015_product_type_columns0/34.5s
t_016_sum_type_columns0/32.9s
t_017_scheduled_columns0/26.2s
t_018_constraints0/34.7s
t_019_many_to_many0/55.6s
t_020_ecs0/75.8s
t_021_multi_column_index0/53.4s