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-5.5

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_check0/17.6s
t_027_private_vs_public_table0/112.6s
t_041_registered_user_gate0/19.3s
t_042_admin_bootstrap0/19.3s
t_043_role_based_access0/110.8s
t_044_ban_list0/116.2s
t_045_rate_limit0/110.3s
t_046_shared_document0/117.7s

basics

0% · 15 evals
StatusTask IDChecksRun Time
t_000_empty_reducers0/111.2s
t_001_basic_tables0/16.9s
t_002_scheduled_table0/113.6s
t_003_struct_in_table0/18.6s
t_004_insert0/27.8s
t_005_update0/314.6s
t_006_delete0/36.5s
t_007_crud0/418.7s
t_008_index_lookup0/36.7s
t_009_init0/46.5s
t_010_connect0/16.4s
t_011_helper_function0/37.4s
t_038_schedule_at_time0/114.0s
t_039_cancel_schedule0/114.6s
t_040_lifecycle_player0/19.4s

data modeling

0% · 6 evals
StatusTask IDChecksRun Time
t_024_event_table0/111.9s
t_025_optional_fields0/110.3s
t_028_cascade_delete0/117.6s
t_029_filter_and_aggregate0/114.7s
t_030_two_table_join0/118.1s
t_031_unique_constraint0/18.5s

queries

0% · 8 evals
StatusTask IDChecksRun Time
t_022_view_basic0/16.7s
t_023_view_per_user0/16.7s
t_032_range_query0/114.2s
t_033_sort_and_limit0/113.2s
t_034_find_first0/112.2s
t_035_select_distinct0/114.7s
t_036_count_without_collect0/112.9s
t_037_multi_column_filter0/117.9s

schema

0% · 10 evals
StatusTask IDChecksRun Time
t_012_spacetime_product_type0/39.1s
t_013_spacetime_sum_type0/38.9s
t_014_elementary_columns0/311.1s
t_015_product_type_columns0/39.5s
t_016_sum_type_columns0/39.4s
t_017_scheduled_columns0/213.6s
t_018_constraints0/312.4s
t_019_many_to_many0/517.9s
t_020_ecs0/716.8s
t_021_multi_column_index0/59.9s