Terminal-Bench 4.0.0 · GPT-5.6 Sol / Codex

||Owned by Terminal-Bench

330 / 330 finished

Started Aug 26, 2026, 6:18 PM · Ran for 28h 13m

324 completed4 timeouts2 errors0 in progress0 pending

harbor run -d terminal-bench/terminal-bench -a codex -m openai/gpt-5.6-sol

{
  "debug": false,
  "quiet": false,
  "retry": {
    "max_retries": 3,
    "max_wait_sec": 60,
    "min_wait_sec": 1,
    "wait_multiplier": 1,
    "exclude_exceptions": [
      "RewardFileNotFoundError",
      "VerifierTimeoutError",
      "AgentTimeoutError",
      "RewardFileEmptyError",
      "VerifierOutputParseError",
      "ApiUsageLimitError"
    ]
  },
  "tasks": [],
  "agents": [
    {
      "name": "codex",
      "kwargs": {
        "version": "0.149.1",
        "reasoning_effort": "max"
      },
      "skills": [],
      "model_name": "openai/gpt-5.6-sol",
      "mcp_servers": [],
      "extra_allowed_hosts": []
    }
  ],
  "metrics": [],
  "datasets": [
    {
      "ref": "4",
      "name": "terminal-bench/terminal-bench",
      "overwrite": false
    }
  ],
  "job_name": "Terminal-Bench 4.0.0 · GPT-5.6 Sol / Codex",
  "jobs_dir": "jobs",
  "verifier": {
    "disable": false
  },
  "artifacts": [],
  "n_attempts": 5,
  "environment": {
    "type": "docker",
    "delete": true,
    "kwargs": {},
    "force_build": false,
    "extra_allowed_hosts": [],
    "extra_docker_compose": [],
    "cpu_enforcement_policy": "auto",
    "memory_enforcement_policy": "auto"
  },
  "credential_mode": "direct",
  "extra_instructions": [],
  "timeout_multiplier": 1,
  "n_concurrent_trials": 330,
  "extra_instruction_paths": []
}