Ramp Accounting Bench
Agents reconcile accounts and prepare financial records across 22 simulated companies. A model grades their answers and files against accounting rubrics.
Ramp uses 137 tasks. Mercor’s earlier APEX-Accounting release uses 100 tasks across ten worlds.
- Made by
- Ramp Labs
- Released
- November 2026
- Kind
- Finance
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- Kept private
- Measures
- Capability
- Subject
- Economics and business
- Language
- English
- Interaction
- Agentic
- Environment
- A simulator
- Refresh
- One fixed set
- Run by
- A host
- In views
- Agents, Robotics, Law and finance
- Strongest model tested
- GPT-6.2 Astra #1 on the capability index
- Last model added
- November 2026
- Scores refreshed
- November 20th, 2026
Gemini 4 Argon leads with 61.1%
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. Every run is in the next chart.
- 61.1
Gemini 4 Argon
- 56.5
Gemini 4 Carbon
- 52.2 Claude Fable 5.2
- 51.7
Gemini 4 Hydrogen
- 50.5 Claude Opus 5.5
- 50.4 GPT-6.2 Astra
- 48.7
Muse Wonder
- 45.6 GPT-6.2 Sol
- 44.1 Grok 4.7
- 43.1 GLM-5.3
- 42.5
Muse Spark 1.3
- 42.5 Claude Sonnet 5.5
- 42.3 Claude Haiku 5.5
- 41.2
Qwen 3.8 Max
- 40.8
DeepSeek V4.1 Flash
- 39.2 Kimi K3
- 35.7 GLM-5.3-Flash
- 34.0 GPT-6 Luna
- 1
Gemini 4 Argon 61.1%
- 2
Gemini 4 Carbon 56.5%
- 3 Claude Fable 5.2 52.2%
- 4
Gemini 4 Hydrogen 51.7%
- 5 Claude Opus 5.5 50.5%
- 6 GPT-6.2 Astra 50.4%
- 7
Muse Wonder 48.7%
- 8 GPT-6.2 Sol 45.6%
- 9 Grok 4.7 44.1%
- 10 GLM-5.3 43.1%
- 11
Muse Spark 1.3 42.5%
- 12 Claude Sonnet 5.5 42.5%
- 13 Claude Haiku 5.5 42.3%
- 14
Qwen 3.8 Max 41.2%
- 15
DeepSeek V4.1 Flash 40.8%
- 16 Kimi K3 39.2%
- 17 GLM-5.3-Flash 35.7%
- 18 GPT-6 Luna 34%
Source: Official Ramp Accounting Bench leaderboard
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | | 61.1% | Mercor Archipelago | Sep 2026 | Oct 2026 | Official leaderboard |
| 2 | | 56.5% | Mercor Archipelago | Oct 2026 | Nov 2026 | Official leaderboard |
| 3 | Claude Fable 5.2 | 52.2% | Mercor Archipelago | Nov 2026 | Nov 2026 | Official leaderboard |
| 4 | | 51.7% | Mercor Archipelago | Nov 2026 | Nov 2026 | Official leaderboard |
| 5 | Claude Opus 5.5 | 50.5% | Mercor Archipelago | Sep 2026 | Sep 2026 | Official leaderboard |
| 6 | GPT-6.2 Astra | 50.4% | Mercor Archipelago | Nov 2026 | Oct 2026 | Official leaderboard |
| 7 | | 48.7% | Mercor Archipelago | Oct 2026 | Oct 2026 | Official leaderboard |
| 8 | GPT-6.2 Sol | 45.6% | Mercor Archipelago | Nov 2026 | Nov 2026 | Official leaderboard |
| 9 | Grok 4.7 | 44.1% | Mercor Archipelago | Sep 2026 | Sep 2026 | Official leaderboard |
| 10 | GLM-5.3 | 43.1% | Mercor Archipelago | Aug 2026 | Sep 2026 | Official leaderboard |
| 11 | | 42.5% | Mercor Archipelago | Sep 2026 | Oct 2026 | Official leaderboard |
| 12 | Claude Sonnet 5.5 | 42.5% | Mercor Archipelago | Sep 2026 | Sep 2026 | Official leaderboard |
| 13 | Claude Haiku 5.5 | 42.3% | Mercor Archipelago | Oct 2026 | Oct 2026 | Official leaderboard |
| 14 | | 41.2% | Mercor Archipelago | Aug 2026 | Aug 2026 | Official leaderboard |
| 15 | | 40.8% | Mercor Archipelago | Sep 2026 | Sep 2026 | Official leaderboard |
| 16 | Kimi K3 | 39.2% | Mercor Archipelago | Jul 2026 | Aug 2026 | Official leaderboard |
| 17 | GLM-5.3-Flash | 35.7% | Mercor Archipelago | Aug 2026 | Aug 2026 | Official leaderboard |
| 18 | GPT-6 Luna | 34% | Mercor Archipelago | Sep 2026 | Sep 2026 | Official leaderboard |
The best score, 61.1%, costs $3.03 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Ramp Accounting Bench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Mercor Archipelago | 61.1% | $3.03 | 86,405 | ||
| Mercor Archipelago | 56.5% | $4.12 | 110,538 | ||
| Claude Fable 5.2 | Mercor Archipelago | 52.2% | $3.71 | 34,457 | |
| Mercor Archipelago | 51.7% | $1.81 | 65,182 | ||
| Claude Opus 5.5 | Mercor Archipelago | 50.5% | $1.34 | 20,064 | |
| GPT-6.2 Astra | Mercor Archipelago | 50.4% | $1.31 | 8,342 | |
| Mercor Archipelago | 48.7% | $2.65 | 23,861 | ||
| GPT-6.2 Sol | Mercor Archipelago | 45.6% | $0.41 | 9,736 | |
| Grok 4.7 | Mercor Archipelago | 44.1% | $3.11 | 55,106 | |
| GLM-5.3 | Mercor Archipelago | 43.1% | $2.16 | 139,788 | |
| Mercor Archipelago | 42.5% | $1.56 | 30,688 | ||
| Claude Sonnet 5.5 | Mercor Archipelago | 42.5% | $0.67 | 20,058 | |
| Claude Haiku 5.5 | Mercor Archipelago | 42.3% | $0.21 | 52,096 | |
| Mercor Archipelago | 41.2% | $2.85 | 63,014 | ||
| Mercor Archipelago | 40.8% | $0.12 | 62,292 | ||
| Kimi K3 | Mercor Archipelago | 39.2% | $1.55 | 30,887 | |
| GLM-5.3-Flash | Mercor Archipelago | 35.7% | $0.18 | 111,748 | |
| GPT-6 Luna | Mercor Archipelago | 34% | $0.05 | 29,709 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Ramp Accounting Bench leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Ramp Accounting Bench 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 11 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (18 entries).
- Pass Models scored 18 models we track.
- Pass Newest score The newest is from November 2026, for GPT-6.2 Astra.
- Pass Frontier models 6 of the top 10 have a score, led by GPT-6.2 Astra (#1).
- Pass Headroom The best is 61.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on labs.ramp.com: 18 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.