Skip to content

Claude Opus 5.5 (effort default (no --effort flag) · thinking on) on Spreadsheet-grade loan amortization for 8 loans incl. rate reset and extra payments

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

Trust 80%Fully autonomoussuccess · first try
Estimated cost
$0.14
Wall time
27s
Human step-ins
0
Outcome
Pass

Compare with other models on this task →

Summary

Exact prompt

# Task: loan amortization (spreadsheet-grade precision) `loans.csv` lists 8 loans: principal, annual_rate_pct (nominal, compounded monthly), years, extra_monthly (extra principal paid each month from `extra_from_month` on, 1-based), optional `rate_reset_month` + `new_rate_pct`. Rules (follow exactly, use decimal arithmetic, round HALF-UP to cents at each step): 1. Scheduled payment = P·i/(1−(1+i)^−n) with i = rate/12/100, n = years·12, rounded to cents. If rate is 0, payment = P/n rounded. 2. Each month: interest = round(balance·i); principal part = payment − interest; plus the extra payment if active. 3. If principal part + extra ≥ remaining balance, the final payment = interest + remaining balance (no extra that month) and the loan ends. 4. At `rate_reset_month` (before computing that month's interest), switch to the new rate and recompute the payment on the current balance over the ORIGINAL remaining term (n − reset_month + 1 months). Write `results.json`: {"L1": {"monthly_payment": "1234.56" (the initial scheduled payment, string), "total_interest": "…" (string, 2dp), "payoff_month": int}, ...} and `L3_schedule.csv` with header `month,payment,interest,principal,balance` (payment includes extra; principal includes extra; strings with 2dp). No network.

Exact-to-the-cent with HALF_UP per-step rounding, 0% loans, final-payment adjustment (one 60-month loan pays off in month 61 due to rounding), payment recompute at rate reset. 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. For each of the 8 loans: monthly_payment and total_interest must equal the key exactly to the cent (Decimal compare), and payoff_month must be exactly right. 2. L3_schedule.csv must have header month,payment,interest,principal,balance and the exact number of rows, with every month and every amount matching exactly.

Setup notes: Use Case Scout batch 4 case d09-loan-amortization-finance (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: $0.140119. Score: 2/2 checks. 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
$0.14
Wall time
27s
Human step-ins
0
Turns
4
Model usage
ModelInput tokOutput tokCost
AClaude Opus 5.5anthropic/claude-opus-5.5effort default (no --effort flag) · thinking on78,1202,675$0.14

Reproduce this run

  1. Use the use case prompt on the use case page.
  2. 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.
  3. It counts as a success only if it meets every success criterion: 1. For each of the 8 loans: monthly_payment and total_interest must equal the key exactly to the cent (Decimal compare), and payoff_month must be exactly right. 2. L3_schedule.csv must have header month,payment,interest,principal,balance and the exact number of rows, with every month and every amount matching exactly.
  4. 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).

Evidence log
[
 {
  "duration_api_ms": 25630,
  "stop_reason": "end_turn",
  "session_id": "[REDACTED]",
  "total_cost_usd": 0.1401188,
  "usage": {
   "input_tokens": 8,
   "cache_creation_input_tokens": 9098,
   "cache_read_input_tokens": 69014,
   "output_tokens": 2675,
   "output_tokens_details": {
    "thinking_tokens": 697
   },
   "server_tool_use": {
    "web_search_requests": 0,
    "web_fetch_requests": 0
   },
   "service_tier": "standard",
   "cache_creation": {
    "ephemeral_1h_input_tokens": 9098,
    "ephemeral_5m_input_tokens": 0
   },
   "inference_geo": "global",
   "iterations": [
    {
     "input_tokens": 2,
     "output_tokens": 811,
     "cache_read_input_tokens": 20549,
     "cache_creation_input_tokens": 695,
     "cache_creation": {
      "ephemeral_5m_input_tokens": 0,
      "ephemeral_1h_input_tokens": 695
     },
     "type": "message"
    }
   ],
   "speed": "standard",
   "fallback_credit": null
  },
  "modelUsage": {
   "claude-opus-5-5": {
    "inputTokens": 8,
    "outputTokens": 2675,
    "cacheReadInputTokens": 69014,
    "cacheCreationInputTokens": 9098,
    "webSearchRequests": 0,
    "costUSD": 0.1401188,
    "contextWindow": 1000000,
    "maxOutputTokens": 128000,
    "thinkingTokens": 697,
    "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": 4,
  "subtype": "success",
  "api_error_status": null,
  "result": "I've written `results.json` and `L3_schedule.csv` (header plus 54 monthly rows). The calculations use decimal arithmetic with half-up rounding to cents at every step, as the rules require. The only check I ran was reading the output by eye: L3's numbers look right, and every loan paid off cleanly.\n\n| Loan | Payment | Total interest | Payoff month |\n|---|---|---|---|\n| L1 | 666.67 | 0.00 | 180 |\n| L2 | 2734.25 | 429664.00 | 297 |\n| L3 | 42.46 | 1316.13 | 54 |\n| L4 | 2000.00 | 0.00 | 60 |\n| L5 | 184.75 | 30423.20 | 300 |\n| L6 | 5835.89 | 42814.62 | **61** |\n| L7 | 48.61 | 9498.22 | 360 |\n| L8 | 4171.56 | 300879.30 | 180 |\n\n**Decision for you: L6 ends one month past its 60-month term.** After its rate reset at month 37, rounding leaves $0.10 owing after month 60. Your rules have no \"pay off whatever is left in the last month\" step, so I followed them literally: month 61 is a $0.10 payment ($0.00 interest + $0.10 principal) and the payoff month is 61. Many spreadsheets would instead add that $0.10 to month 60's payment, which would give a payoff month of 60 with the same total interest. Tell me if you want that and I'll change it.\n\nHow the special cases came out:\n- **L3:** the extra $250 starts in month 25. At month 37 the rate resets to 6.75% and the payment is recalculated on the 4,552.75 balance over 324 months, giving 30.58 (280.58 with the extra). The last payment, in month 54, is 17.71.\n- **L1:** at 0%, the payment is 666.67. The final payment is 666.07, so the extra cents from rounding up aren't overpaid.\n- **L2:** paid off in month 297 thanks to the extra payments from month 25.\n- **L8:** its `extra_from_month` of 25 has no effect because its extra amount is 0.\n\nThe script is `../scripts/amort.py`. Run it from the `work` folder with `python3 -I ../scripts/amort.py loans.csv`.",
  "ttft_ms": 2195,
  "type": "result",
  "duration_ms": 26019,
  "uuid": "[REDACTED]",
  "ttft_stream_ms": 1093,
  "time_to_request_ms": 235,
  "first_content_frame_ms": 1093,
  "queued_turn_count": 0,
  "result_index": 0
 }
]

Get new runs and ranking changes weekly