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.

Gemini 3.1 Pro

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_027_private_vs_public_table0/113.3s
t_044_ban_list0/113.2s
t_046_shared_document0/112.8s
t_045_rate_limit0/113.1s
t_026_auth_identity_check0/112.7s
t_041_registered_user_gate0/114.8s
t_042_admin_bootstrap0/112.7s
t_043_role_based_access0/112.7s

basics

0% · 15 evals
StatusTask IDChecksRun Time
t_003_struct_in_table0/17.8s
t_000_empty_reducers0/112.9s
t_001_basic_tables0/18.4s
t_002_scheduled_table0/112.2s
t_004_insert0/28.2s
t_005_update0/312.4s
t_006_delete0/311.1s
t_007_crud0/411.0s
t_008_index_lookup0/311.7s
t_009_init0/410.0s
t_010_connect0/18.0s
t_011_helper_function0/37.4s
t_038_schedule_at_time0/112.9s
t_039_cancel_schedule0/112.8s
t_040_lifecycle_player0/19.2s

data modeling

0% · 6 evals
StatusTask IDChecksRun Time
t_024_event_table0/16.7s
t_025_optional_fields0/19.0s
t_028_cascade_delete0/110.6s
t_029_filter_and_aggregate0/111.3s
t_030_two_table_join0/113.1s
t_031_unique_constraint0/17.6s

queries

0% · 8 evals
StatusTask IDChecksRun Time
t_034_find_first0/112.5s
t_035_select_distinct0/114.8s
t_036_count_without_collect0/114.2s
t_037_multi_column_filter0/113.7s
t_022_view_basic0/112.6s
t_023_view_per_user0/19.0s
t_032_range_query0/113.6s
t_033_sort_and_limit0/114.3s

schema

0% · 10 evals
StatusTask IDChecksRun Time
t_020_ecs0/712.8s
t_012_spacetime_product_type0/332.5s
t_013_spacetime_sum_type0/326.1s
t_014_elementary_columns0/322.9s
t_015_product_type_columns0/325.2s
t_016_sum_type_columns0/39.4s
t_017_scheduled_columns0/213.1s
t_018_constraints0/311.6s
t_019_many_to_many0/529.5s
t_021_multi_column_index0/58.6s