Accounting Autocoding
Models select a bookkeeping category for each expense. Ramp checks the first choice against the assigned category.
- Made by
- Ramp Labs
- Released
- March 2026
- Kind
- Finance
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- Kept private
- Measures
- Capability
- Subject
- Economics and business
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- A host
- In views
- Law and finance
- Strongest model tested
- GPT-5.4 #28 on the capability index
- Last model added
- March 2026
- Scores refreshed
- November 20th, 2026
Gemini 3.1 Pro leads with 92.6% among models released by March 2026
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in March 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 92.6
Gemini 3.1 Pro
- 92.0
Gemini 2.5 Pro
- 92.0
Gemini 3 Pro
- 91.9 Claude Opus 4.6
- 91.6 GLM-5
- 91.5 Claude Opus 4.5
- 91.4
Gemini 3 Flash
- 91.3 Claude Sonnet 4.6
- 90.7 GPT-5.4
- 90.6 Kimi K2.5
- 90.5
Gemini 2.5 Flash
- 90.4 Claude Sonnet 4.5
- 90.1
Gemini 2.0 Flash
- 90.1 GPT-5.1
- 90.0 GPT-5 mini
- 90.0
MiniMax-M2.5
- 89.7 Claude Haiku 4.5
- 89.4 GPT-5.2
- 88.5
Gemini 2.0 Flash-Lite
- 88.2 GPT-4.1 mini
- 87.9
Gemini 2.5 Flash-Lite
- 1
Gemini 3.1 Pro 92.6%
- 2
Gemini 2.5 Pro Jun 2025 92%
- 3
Gemini 3 Pro 92%
- 4 Claude Opus 4.6 91.9%
- 5 GLM-5 91.6%
- 6 Claude Opus 4.5 91.5%
- 7
Gemini 3 Flash 91.4%
- 8 Claude Sonnet 4.6 91.3%
- 9 GPT-5.4 90.7%
- 10 Kimi K2.5 90.6%
- 11
Gemini 2.5 Flash Sep 2025 90.5%
- 12 Claude Sonnet 4.5 90.4%
- 13
Gemini 2.0 Flash Feb 2025 90.1%
- 14 GPT-5.1 90.1%
- 15 GPT-5 mini 90%
- 16
MiniMax-M2.5 90%
- 17 Claude Haiku 4.5 89.7%
- 18 GPT-5.2 89.4%
- 19
Gemini 2.0 Flash-Lite 88.5%
- 20 GPT-4.1 mini 88.2%
- 21
Gemini 2.5 Flash-Lite Sep 2025 87.9%
Source: Official Accounting Autocoding leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 92.6% | Feb 2026 | Official leaderboard | |
| 2 | | 92% | Jun 2025 | Official leaderboard | |
| 3 | | 92% | Nov 2025 | Official leaderboard | |
| 4 | Claude Opus 4.6 | 91.9% | Feb 2026 | Official leaderboard | |
| 5 | GLM-5 | 91.6% | Feb 2026 | Official leaderboard | |
| 6 | Claude Opus 4.5 | 91.5% | Nov 2025 | Official leaderboard | |
| 7 | | 91.4% | Dec 2025 | Official leaderboard | |
| 8 | Claude Sonnet 4.6 | 91.3% | Feb 2026 | Official leaderboard | |
| 9 | GPT-5.4 | 90.7% | Mar 2026 | Official leaderboard | |
| 10 | Kimi K2.5 | 90.6% | Jan 2026 | Official leaderboard | |
| 11 | | 90.5% | Sep 2025 | Official leaderboard | |
| 12 | Claude Sonnet 4.5 | 90.4% | Sep 2025 | Official leaderboard | |
| 13 | | 90.1% | Feb 2025 | Official leaderboard | |
| 14 | GPT-5.1 | 90.1% | Nov 2025 | Official leaderboard | |
| 15 | GPT-5 mini | 90% | Aug 2025 | Official leaderboard | |
| 16 | | 90% | Feb 2026 | Official leaderboard | |
| 17 | Claude Haiku 4.5 | 89.7% | Oct 2025 | Official leaderboard | |
| 18 | GPT-5.2 | 89.4% | Dec 2025 | Official leaderboard | |
| 19 | | 88.5% | Feb 2025 | Official leaderboard | |
| 20 | GPT-4.1 mini | 88.2% | Apr 2025 | Official leaderboard | |
| 21 | | 87.9% | Sep 2025 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Accounting Autocoding leaderboard
Gemini 2.0 Flash on the official leaderboard passed 85% in February 2025
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Accounting Autocoding leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Law, finance and medicine
- MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy.
Qwen 3.8 Max 80.4%
- HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
- HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
- FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy.
Ling-3.1-flash 81.7%
- KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
- Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (21 entries).
- Pass Models scored 21 models we track.
- Note Newest score The newest came 8 months ago, in March 2026, for GPT-5.4. That’s expected for a saturated test.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5.4 (#28).
- Note Headroom Saturated. The best is 92.6%, past 85% since February 2025.
Leaderboard import 3 pass
- Pass Importer We read the board on builders.ramp.com: 21 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.