Dayjob: Tax – evaluating AI agents on 50 professional tax assignments
Surge AI introduces DAYJOB: Tax, a benchmark of 50 environments evaluating AI agents on professional tax assignments across eight practice areas. Agents receive client requests and records, then produce returns, workpapers, reviews, or advice. Results are reported as pass@1 at a 95% rubric threshold. Claude Sonnet 5.5 leads with a 10.8% pass rate, followed by Claude Fable 5.1 at 9.6% and Claude Opus 5.5 at 9.2%. The post illustrates failures where agents missed a sale-eligibility deadline and failed to verify a couple's marital status despite evidence in the files.
Open original source surgehq.aiOne primary source; other links are context, not independent corroboration.
- Primary sourceHacker News · AI
- Discovery linkHacker News
- Linked in sourceSurge AI's DAYJOB benchmark family
- Linked in sourceDAYJOB: Tax leaderboard
- Linked in sourceTaxBench
- Linked in sourceTaxCalcBench
- Linked in sourceTaxLab
A community post points to the original link. Discussion and upvotes do not establish accuracy.
Open full article view →- Community discussion+5
- Fetched source page+30
- No editor link review+0
- Community link+0
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
Surge AI introduces DAYJOB: Tax, a benchmark of 50 environments evaluating AI agents on professional tax assignments across eight practice areas. Agents receive client requests and records, then produce returns, workpapers, reviews, or advice. Results are reported as pass@1 at a 95% rubric threshold. Claude Sonnet 5.5 leads with a 10.8% pass rate, followed by Claude Fable 5.1 at 9.6% and Claude Opus 5.5 at 9.2%. The post illustrates failures where agents missed a sale-eligibility deadline and failed to verify a couple's marital status despite evidence in the files.
A READER'S EVIDENCE CHECKHow to read this signalSix questions about claims, sources, risks, and open checks
This is a signal-level guide until claim-level evidence is available. “Not recorded” means the evidence has not been assessed here; it does not mean a result is false. How we check AI news →
- 01Who is making each claim?
The claimant and whether each claim was measured or asserted are not recorded in this public brief.
- 02What was actually tested?
Not recorded per claim. Check the source for sample size, tasks, model and benchmark versions, and reproducibility.
- 03Where are the sources?
Original link: surgehq.ai. Brief basis: fetched source page. Primary page date and quote locations are not established in this panel.
- 04What could mislead?
Source claims not independently checked; the benchmark and rubric are defined by the publisher, and pass rates reflect its specific grading criteria.
- 05What is at risk if wrong?
Not assessed per claim. Consider safety, privacy, cost, and adoption decisions before relying on the result.
- 06What would change the view?
No claim-specific check is recorded. An inspectable primary method or independent replication could change the assessment.
Key findings from the stored brief
- Claude Sonnet 5.5 leads the DAYJOB: Tax leaderboard with a 10.8% pass rate at a 95% rubric threshold.
- Across five attempts, one agent never identified a residence-requirement deadline that Opus identified in all five.
- The benchmark has 50 environments across eight tax practice areas with 1,789 workspace files.
- Opus assumed a couple was unmarried in all five attempts despite records suggesting possible valid marriage elsewhere.
Source claims not independently checked; the benchmark and rubric are defined by the publisher, and pass rates reflect its specific grading criteria.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
A community post points to the original link. Discussion and upvotes do not establish accuracy.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
A publication revision history is not stored for this signal. New engagement snapshots do not mean the source itself changed.
Why this may matter
The results suggest current agents struggle with the professional judgment tax work requires, such as spotting unasked-about consequential issues and verifying evidence, not just calculations. Low pass rates indicate substantial remaining gaps.
Limits and open questions
Source claims not independently checked; the benchmark and rubric are defined by the publisher, and pass rates reflect its specific grading criteria.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Discussion
Comments are reviewed before publication. Discuss the evidence, not the person.
No published comments yet.
Reader discussion opens with accounts. You can read the original source and published comments now.