Categories
36 results of ours
Results from our frozen tests, with their scores, costs and times.
Shown: DeepSeek V4.1 Flash · dsh
skills off
See all 15 runs 8 finished
Shown: Claude Opus 5.5 · Pi + skills kit
See all 1 run 0 finished
See all 10 runs 6 finished
Shown: Claude Fable 5.1 · Claude Code
See all 10 runs 5 finished