Claude Opus 5.5 (effort default (no --effort flag) · thinking on) on Schedule a 40-task build DAG on 3 workers with exclusive resources

AClaude Opus 5.5default · thinking on · Claude Code 2.1.299 (headless -p) · cloud · 2026-10-16 · by @bobsiopener

Trust 80%Fully autonomoussuccess · first tryCompare

Estimated cost: $0.47
Wall time: 1.7h
Human step-ins: 0
Outcome: Pass

Compare with other models on this task →

Exact prompt

# Task: schedule a build `tasks.json` describes 40 build tasks: duration (minutes), dependencies, and resources each task holds while running. There are `workers` identical workers (each runs one task at a time) and resource limits (at most `db: 1` and `net: 2` tasks holding that resource concurrently). Tasks can't be preempted; a task may start only when all its deps have finished (start ≥ max dep end time). Produce `schedule.json`: {"t00": {"start": <int minute>, "worker": <0..workers-1>}, ...} for ALL tasks, minimising the makespan (time the last task finishes). Also write `plan_notes.md` with your makespan and the lower bound you computed (max of critical path and total work / workers). You may write code. No network.

Validator checks deps, worker overlap, resource limits; must match or beat critical-path list scheduling (makespan 98; lower bound 91). Original benchmark task written for usecaserank.com (not based on a specific public post). Headless, offline run on a reproducible fixture. Each run's notes say how its cost was measured (estimates are marked).

Success criteria: 1. schedule.json must contain exactly the 40 tasks, each with a non-negative integer start and a valid worker index. 2. No task starts before all its dependencies finish. 3. No two tasks overlap on the same worker. 4. At no start time do concurrent tasks exceed the db (1) or net (2) resource limits. 5. Makespan <= the reference critical-path list-scheduling makespan.

Setup notes: Use Case Scout batch 4 case d12-build-scheduler (offline fixture). Prepared with batch4/prepare.sh; hidden key/tests kept outside the agent's work dir. Prompt = TASK.md verbatim. Scored with the scout's scorer: `python score.py WORKDIR KEYDIR/key.json`. Tools: Read/Write/Edit/Glob/Grep/Bash, web disabled. Single run, no retries. Claude Code's own reported cost for claude-opus-5.5: $0.467787. Score: pass. Cost is an ESTIMATE: measured tokens x pricing.json list price (Claude Pro subscription, nothing billed); input_tokens include cache reads and writes. Single run.

Estimated cost List-price estimate; not actually billed.

Metrics

Estimated cost: $0.47
Wall time: 1.7h
Human step-ins: 0
Turns: 13

Model usage
Model	Input tok	Output tok	Cost
AClaude Opus 5.5anthropic/claude-opus-5.5effort default (no --effort flag) · thinking on	315,170	8,218	$0.47

Reproduce this run

Use the use case prompt on the use case page.
Same setup: Claude Opus 5.5 (anthropic/claude-opus-5.5, effort default (no --effort flag) · thinking on) via Claude Code 2.1.299 (headless -p), cloud.
It counts as a success only if it meets every success criterion: 1. schedule.json must contain exactly the 40 tasks, each with a non-negative integer start and a valid worker index. 2. No task starts before all its dependencies finish. 3. No two tasks overlap on the same worker. 4. At no start time do concurrent tasks exceed the db (1) or net (2) resource limits. 5. Makespan <= the reference critical-path list-scheduling makespan.
Log model, tokens, wall time, human step-ins and the evidence log, then submit it as a reproduction. A different model? Submit a head-to-head rerun.

How runs are scored: Methodology.

Was this useful?

⇄ Rerun on another model

Automated checks

Trust 80% comes from these checks (how Trust % works).

Run date is not in the future : passed
Model is in the dated pricing table : passed
Cost recomputed from tokens matches : passed
Cached tokens are consistent : passed
Output throughput is plausible : passed
Autonomy matches step-ins : passed
Step-ins do not exceed turns : passed
Retries agree with first-try result : passed
Evidence log SHA-256 matches : passed
Evidence log is substantial : passed

Evidence log

[
 {
  "duration_api_ms": 180246,
  "stop_reason": "end_turn",
  "session_id": "[REDACTED]",
  "total_cost_usd": 0.46778739999999996,
  "usage": {
   "input_tokens": 26,
   "cache_creation_input_tokens": 30807,
   "cache_read_input_tokens": 284337,
   "output_tokens": 8218,
   "output_tokens_details": {
    "thinking_tokens": 2042
   },
   "server_tool_use": {
    "web_search_requests": 0,
    "web_fetch_requests": 0
   },
   "service_tier": "standard",
   "cache_creation": {
    "ephemeral_1h_input_tokens": 30807,
    "ephemeral_5m_input_tokens": 0
   },
   "inference_geo": "global",
   "iterations": [
    {
     "input_tokens": 2,
     "output_tokens": 516,
     "cache_read_input_tokens": 30364,
     "cache_creation_input_tokens": 776,
     "cache_creation": {
      "ephemeral_5m_input_tokens": 0,
      "ephemeral_1h_input_tokens": 776
     },
     "type": "message"
    }
   ],
   "speed": "standard",
   "fallback_credit": null
  },
  "modelUsage": {
   "claude-opus-5-5": {
    "inputTokens": 26,
    "outputTokens": 8218,
    "cacheReadInputTokens": 284337,
    "cacheCreationInputTokens": 30807,
    "webSearchRequests": 0,
    "costUSD": 0.46778739999999996,
    "contextWindow": 1000000,
    "maxOutputTokens": 128000,
    "thinkingTokens": 2042,
    "canonicalModel": "claude-opus-5-5",
    "provider": "firstParty",
    "costBasis": "list"
   }
  },
  "permission_denials": [],
  "terminal_reason": "completed",
  "fast_mode_state": "off",
  "fast_mode_disabled_reason": "sdk_opt_in_required",
  "subagent_stats": {
   "spawned": 0,
   "requested": {
    "background": 0,
    "foreground": 0,
    "unset": 0
   },
   "started_in_background": 0,
   "max_depth": 0,
   "spawned_by_subagents": 0,
   "completed": 0,
   "failed": 0,
   "killed": {
    "parent": 0,
    "user": 0,
    "system": 0
   },
   "refused": {
    "depth_limit": 0,
    "concurrency_limit": 0,
    "budget": 0
   },
   "by_type": {}
  },
  "safety_stops": 0,
  "is_error": false,
  "num_turns": 13,
  "subtype": "success",
  "api_error_status": null,
  "result": "I've written `schedule.json` with a 95-minute makespan, and a separate checker confirmed it's valid: all dependencies, worker overlaps and the `db`/`net` limits hold.\n\n**Lower bound: 91 minutes.**\n- The critical path is 81 minutes: t00 \u2192 t01 \u2192 t02 \u2192 t04 \u2192 t07 \u2192 t08 \u2192 t20 \u2192 t27.\n- Total work is 273 minutes over 3 workers, which rounds up to 91.\n\n**There's a 4-minute gap I couldn't close or prove away.** Two search methods both stopped at 95:\n- **Priority-based scheduling:** about 200,000 randomized runs that favour tasks with the longest remaining chain behind them.\n- **Simulated annealing:** reordering tasks and rebuilding the schedule, over 17 random seeds.\n\nNo solver library that could prove the best possible answer was installed, so I can't say whether 95 is optimal. Three other bounds I tried didn't beat 91: `db` work alone (88), `net` work (79) and a tighter `db`-only bound (88).\n\n**`db` is the bottleneck.** It needs 88 minutes of one-at-a-time work, and t08, the longest `db` task, can't start before minute 42.\n\n`plan_notes.md` has the makespan, the bounds and the method. The scripts are in `../scripts/`, outside the task directory.\n\nSeparately, one command output included an unexpected list of `./usecase-publisher/...` file paths and a CSS snippet. It wasn't from anything I ran, so I ignored it.",
  "ttft_ms": 2149,
  "type": "result",
  "duration_ms": 278237,
  "uuid": "[REDACTED]",
  "ttft_stream_ms": 985,
  "time_to_request_ms": 233,
  "first_content_frame_ms": 986,
  "queued_turn_count": 0,
  "result_index": 0
 }
]