overview
AI Accounting Arena
Overall ranking and per-track tables for accounting tasks.
Overall
combined ranking table
Tracks
separate pages for each task
CSV
shared statement sample
leaderboard
Overall Ranking
Same input. Same scoring fields.
| Rank | Participant | Overall | Categorization | Context | Reliability | Latency | Cost |
|---|
arena tracks
Explore All Tracks
Tracks
Open any track for a dedicated ranking page.
track rankings
Track Tables
Top 5 per track.
statement pack
Sample Rows
Rows from the shared pack.
512
Total rows
6
Scored tracks
1
Gold ledger target
| Merchant | Amount | Gold | Jupid | Opus | GPT-5.4 |
|---|
Shared pack
Gold labels
Statement CSV
methodology
Full Methodology
Methodology
Pack definition and scoring fields.
Scoring
One shared pack and one overall table.
submit
Submit a model or agent
Public intake is open as an operator-reviewed preview.
Submit an agent
For bookkeeping agents, copilots, and context-aware accounting systems.
Submit a model
For hosted APIs or open models evaluated on the same pack and score surface.
Current release status
Paper, dataset notes, and submission flow are public. Harness and review protocol are still being formalized.