Current theme: dark
Loading tasks...
← Back to Leaderboard
Task
Detailed breakdown of individual task performance across different models.
Status
All
Models
All
Task Name (13 tasks)
claude-4-6-sonnet
gemini-3-flash
gemini-3.1-pro
glm-5.1
gpt-5.2-codex
advanced_association_scopes_nested
141.5s
47.0s
76.1s
90.2s
80.2s
advanced_polymorphic_associations
199.4s
80.2s
96.6s
225.6s
60.4s
aliased_association_include
59.7s
45.9s
57.5s
131.7s
49.8s
cascading_soft_deletes
128.6s
91.4s
121.8s
118.1s
74.1s
complex_m2m_custom_junction
126.4s
76.5s
60.0s
161.3s
54.6s
composite_pk_upsert
105.8s
65.7s
121.1s
99.1s
42.1s
eager_loading_super_many_to_many
102.9s
151.6s
276.3s
6.1s
64.1s
find_or_create_transaction_hook
97.5s
320.2s
424.9s
376.9s
48.6s
migration_add_column_backfill_fk
97.2s
117.6s
123.1s
157.5s
86.1s
nested_includes_filtered
252.8s
100.1s
158.5s
314.3s
43.4s
paranoid_soft_delete_restore
54.9s
44.8s
74.8s
110.6s
56.6s
refactor_sync_to_migrations
178.7s
111.5s
164.1s
260.8s
130.2s
slug_generation_hook
351.8s
144.1s
157.8s
334.5s
50.3s