Fill and submit job applications from a resume
Exact prompt
This is a sandboxed mock job portal. resume.json is the candidate. forms/ has two job application forms (field definitions). For each form, write a JSON file {"job_id": ..., "answers": {field_name: value}} filled truthfully from the resume (never invent facts), then submit it with: python3 submit.py <file>. Fix and resubmit if rejected. Both applications must end up SUBMITTED.
Task prompt given to the agent (headless, offline, synthetic fixture inputs): This is a sandboxed mock job portal. resume.json is the candidate. forms/ has two job application forms (field definitions). For each form, write a JSON file {"job_id": ..., "answers": {field_name: value}} filled truthfully from the resume (never invent facts), then submit it with: python3 submit.py <file>. Fix and resubmit if rejected. Both applications must end up SUBMITTED. Inspired by https://x.com/SAkasxh/status/2104655629021565156 (unverified; not checked with the author). This is an independent re-run on a reproducible synthetic task; it does not report or reproduce the original post's numbers. Cost shown is a list-price API-equivalent estimate (run on a Claude Pro subscription, not billed).
Success criteria: All automated rubric checks pass: ACME submitted; Globex submitted; ACME identity fields match resume; ACME years_experience = 6-9; ACME authorized = yes; ACME skills only from resume; Globex names/title/email match; Globex relocation false; Globex salary = 165000; Globex linkedin from resume (if given).
Best model for this task so far: Gemma 4 31B Instruct (Venice) (success, $0.0019, 49s).
All runs (8)
100% pass rate across 8 eligible runs: 8 pass, 0 partial, 0 fail. Partial and failed runs are listed below with everything else.ⓘ
| Model | Cost | Time | Step-insⓘ | Autonomy | Outcome | Trustⓘ | Date | Compare |
|---|---|---|---|---|---|---|---|---|
| ZGLM 5.3 (Venice)thinking on | $0.01 | 13s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-17 | |
| AClaude Haiku 5.5default · thinking on | $0.0044 | 17s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-16 | |
| XGrok 4.3 (Venice) | $0.02 | 16s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-15 | |
| QQwen3 Coder 480B Turbo (Venice) | $0.0023 | 15s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-15 | |
| DDeepSeek V4.1 Flash (Venice) | $0.0024 | 50s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-14 | |
| GGemma 4 31B Instruct (Venice) | $0.0019 | 49s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-14 | |
| AClaude Opus 5.5 | $0.10 | 18s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-14 | |
| AClaude Sonnet 5.5 | $0.05 | 11s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-14 |
Embed this result
A live badge for this use case. It links back here and updates as new runs are published.
Get new runs and ranking changes weekly
Which models got better or cheaper on real tasks like this one.