math-eval-grader__dd8fc756

terminal-bench/terminal-bench|terminal-bench/math-eval-grader|codex@0.159.0|openai/gpt-6.1-sol

harbor run -d terminal-bench/terminal-bench -t terminal-bench/math-eval-grader -a codex -m openai/gpt-6.1-sol

harbor run -d terminal-bench/terminal-bench -t terminal-bench/math-eval-grader -a codex -m openai/gpt-6.1-sol

Outcome

9/30/2026, 12:59:20 AM

Statuscompleted

Reward0.00

CostLoading...

Tokens

Output

Prompt

Cached

Loading tokens...

Timing

Env Setup (12s, scaled)

Agent Setup (2m 5s)

Agent Execution (22m 9s)

Verifier (52s)

25m 41s

Trajectory

Tool call

Observation

Reasoning