工具条件未记录 / max / Claude Code --bare mode · Terminal-Bench 4.0; Claude Code --bare; max thinking effort; 66 tasks, ten trials per task (660 trials); no internet.
Terminal-Bench · 4.0 · Score · 工具条件未记录 / max / Claude Code --bare mode · Terminal-Bench 4.0; Claude Code --bare; max thinking effort; 66 tasks, ten trials per task (660 trials); no internet.
工具条件未记录 / max / 框架未记录 · Terminal-Bench 4.0; 66 tasks; ten trials per task (660 trials); Claude Code --bare at max thinking effort.
Terminal-Bench · 4.0 · Score · 工具条件未记录 / max / 框架未记录 · Terminal-Bench 4.0; 66 tasks; ten trials per task (660 trials); Claude Code --bare at max thinking effort.
Regular display scope. Rankings are grouped by metric and evaluation protocol. Recorded tool access, budgets, and frameworks are shown separately. Scores remain available for reference when conditions are unspecified.
Score %
Tool access not recorded / max / Claude Code --bare mode · Terminal-Bench 4.0; Claude Code --bare; max thinking effort; 66 tasks, ten trials per task (660 trials); no internet.
Terminal-Bench · 4.0 · Score · Tool access not recorded / max / Claude Code --bare mode · Terminal-Bench 4.0; Claude Code --bare; max thinking effort; 66 tasks, ten trials per task (660 trials); no internet.
Tool access not recorded / max / Framework not recorded · Terminal-Bench 4.0; 66 tasks; ten trials per task (660 trials); Claude Code --bare at max thinking effort.
Terminal-Bench · 4.0 · Score · Tool access not recorded / max / Framework not recorded · Terminal-Bench 4.0; 66 tasks; ten trials per task (660 trials); Claude Code --bare at max thinking effort.
Tool access not recorded / max / Claude Code --bare mode · Terminal-Bench 4.0, 66 tasks, five trials per task (330 trials).
Terminal-Bench · 4.0 · Score · Tool access not recorded / max / Claude Code --bare mode · Terminal-Bench 4.0, 66 tasks, five trials per task (330 trials).