mypcbench

anonymousmypcbench

AI & ML interests

None yet

Recent Activity

updated a dataset 28 days ago

anonymousmypcbench/mypcbench-claude-opus-4-6-trajectories

published a dataset 28 days ago

anonymousmypcbench/mypcbench-claude-opus-4-6-trajectories

new activity about 2 months ago

anonymousmypcbench/cua-speedrun-trajectories:Publish GPT-6 Astra MyPCBench reasoning sweep

View all activity

Organizations

None yet

updated a dataset 28 days ago

anonymousmypcbench/mypcbench-claude-opus-4-6-trajectories

Updated 28 days ago • 178 • 1

published a dataset 28 days ago

anonymousmypcbench/mypcbench-claude-opus-4-6-trajectories

Updated 28 days ago • 178 • 1

New activity in anonymousmypcbench/cua-speedrun-trajectories about 2 months ago

Publish GPT-6 Astra MyPCBench reasoning sweep

#25 opened about 2 months ago by

Add Yutori n2 Energy50 reasoning-effort sweep

#23 opened about 2 months ago by

Add GPT-5.6 Sol and Luna low Energy50 evaluations 62 and 63

#21 opened about 2 months ago by

Add GPT-5.6 Luna via Codex low/medium/high/xhigh Energy50 evaluations 153–156

#22 opened about 2 months ago by

Add corrected GLM thinking-off trajectories (evals 87 and 88)

#20 opened about 2 months ago by

Add six Kimi K3 parallel Energy50 and OSWorld2 K52 evaluations

#17 opened about 2 months ago by

Add GPT-6 Astra medium/high Energy50 no-preload evaluations 151 and 152

#19 opened about 2 months ago by

Add Gemini 3.8 Flash Energy50 evaluations 59, 60, and 61

#18 opened about 2 months ago by

Add Claude Opus 5 and Sonnet 5 low OSWorld2 K52 evaluations 57 and 58

#16 opened about 2 months ago by

Add GPT-6 Astra low/xhigh CUA-World K26 evaluations 137 and 139 trajectories

#15 opened about 2 months ago by

Add Muse Spark 1.3 OSWorld2 K52 trajectories

#14 opened about 2 months ago by

Add Gemini 3.8 Flash and GPT-6 Astra evaluation trajectories

#11 opened about 2 months ago by

Add Gemini 3.8 Flash OSWorld2 K52 evaluations 54–56

#13 opened about 2 months ago by

Add OSWorld2 K52 evaluation trajectories

#12 opened about 2 months ago by

New activity in anonymousmypcbench/cua-speedrun-trajectories 2 months ago

Remove the 1.1 xhigh archive that lost 7 tasks to a billing outage

#10 opened 2 months ago by

Add energy50 trajectories: Muse Spark 1.1/1.2, GLM-5V, MiniMax-M3

#8 opened 2 months ago by

Add OSWorld Energy50 trajectory exports

#6 opened 3 months ago by

Add OSWorld Energy50 reasoning-effort trajectories

#5 opened 3 months ago by