Agentic Credit Analysis
Models extract and standardize income statements and balance sheets. Ramp compares their figures with credit analysts’ figures using a five percent tolerance.
- Made by
- Ramp Labs
- Released
- October 2026
- Kind
- Finance
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Kept private
- Measures
- Capability
- Subject
- Economics and business
- Language
- English
- Interaction
- Agentic
- Environment
- APIs and tools
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A host
- Occupations
- Business and financial operations
- In views
- Agents, Law and finance
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
Ramp pipeline + GPT-6 Luna tops the leaderboard with 84.4% Claude Sonnet 5.5 leads with 80.2% among models released by September 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran on its own with several settings, we keep its best. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. The best model on its own is Claude Sonnet 5.5, at 80.2%. Agents built around a model, such as Ramp pipeline + GPT-6 Luna, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.
The newest model with a score here came out in September 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-6.1 Sol
- and 12 more
- 84.4 Ramp pipeline + GPT-6 Luna
- 84.0 Ramp pipeline + GPT-6 Sol
- 83.3 Ramp pipeline + Claude Sonnet 5.5
- 82.0 Ramp pipeline + Claude Opus 5.5
- 80.3 Ramp pipeline + Gemini 3.1 Pro
- 80.2 Claude Sonnet 5.5
- 80.0 Claude Opus 5.5
- 78.5
Gemini 3.8 Flash
- 78.3
Gemini 3.1 Pro
- 78.3 GPT-6 Sol
- 77.9 GPT-6 Luna
- 77.6 Ramp pipeline + Gemini 3.8 Flash
- 77.3 Ramp pipeline + GPT-6 Astra
- 61.1 GPT-6 Astra
- 1 Ramp pipeline + GPT-6 Luna 84.4%
- 2 Ramp pipeline + GPT-6 Sol 84%
- 3 Ramp pipeline + Claude Sonnet 5.5 83.3%
- 4 Ramp pipeline + Claude Opus 5.5 82%
- 5 Ramp pipeline + Gemini 3.1 Pro 80.3%
- 6 Claude Sonnet 5.5 80.2%
- 7 Claude Opus 5.5 80%
- 8
Gemini 3.8 Flash 78.5%
- 9
Gemini 3.1 Pro 78.3%
- 10 GPT-6 Sol 78.3%
- 11 GPT-6 Luna 77.9%
- 12 Ramp pipeline + Gemini 3.8 Flash 77.6%
- 13 Ramp pipeline + GPT-6 Astra 77.3%
- 14 GPT-6 Astra 61.1%
Source: Official Agentic Credit Analysis leaderboard
- 1 Claude Sonnet 5.5 80.2%
- 2 Claude Opus 5.5 80%
- 3
Gemini 3.8 Flash 78.5%
- 4
Gemini 3.1 Pro 78.3%
- 5 GPT-6 Sol 78.3%
- 6 GPT-6 Luna 77.9%
- 7 GPT-6 Astra 61.1%
Source: Official Agentic Credit Analysis leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Ramp pipeline + GPT-6 Luna | 84.4% | Sep 2026 | Official leaderboard | |
| 2 | Ramp pipeline + GPT-6 Sol | 84% | Sep 2026 | Official leaderboard | |
| 3 | Ramp pipeline + Claude Sonnet 5.5 | 83.3% | Sep 2026 | Official leaderboard | |
| 4 | Ramp pipeline + Claude Opus 5.5 | 82% | Sep 2026 | Official leaderboard | |
| 5 | Ramp pipeline + Gemini 3.1 Pro | 80.3% | Feb 2026 | Official leaderboard | |
| 6 | Claude Sonnet 5.5 | 80.2% | Sep 2026 | Official leaderboard | |
| 7 | Claude Opus 5.5 | 80% | Sep 2026 | Official leaderboard | |
| 8 | | 78.5% | Sep 2026 | Official leaderboard | |
| 9 | | 78.3% | Feb 2026 | Official leaderboard | |
| 10 | GPT-6 Sol | 78.3% | Sep 2026 | Official leaderboard | |
| 11 | GPT-6 Luna | 77.9% | Sep 2026 | Official leaderboard | |
| 12 | Ramp pipeline + Gemini 3.8 Flash | 77.6% | Sep 2026 | Official leaderboard | |
| 13 | Ramp pipeline + GPT-6 Astra | 77.3% | Sep 2026 | Official leaderboard | |
| 14 | GPT-6 Astra | 61.1% | Sep 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Sonnet 5.5 | 80.2% | Sep 2026 | Official leaderboard | |
| 2 | Claude Opus 5.5 | 80% | Sep 2026 | Official leaderboard | |
| 3 | | 78.5% | Sep 2026 | Official leaderboard | |
| 4 | | 78.3% | Feb 2026 | Official leaderboard | |
| 5 | GPT-6 Sol | 78.3% | Sep 2026 | Official leaderboard | |
| 6 | GPT-6 Luna | 77.9% | Sep 2026 | Official leaderboard | |
| 7 | GPT-6 Astra | 61.1% | Sep 2026 | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s own leaderboard: P&L and Balance sheet. Each ranks models on one part of the test. Claude Opus 5.5 leads P&L and Gemini 3.1 Pro leads Balance sheet. Arrows show how far a model moved from its overall rank among the models we track.
P&L
7 models we track have a score here.
- 1 Claude Opus 5.5 ↑1 77.6%
- 2 Claude Sonnet 5.5 ↓1 77%
- 3 GPT-6 Sol ↑2 76.3%
- 4 GPT-6 Luna ↑2 75.7%
- 5
Gemini 3.8 Flash ↓2 74.2%
- 6
Gemini 3.1 Pro ↓2 73.2%
- 7 GPT-6 Astra 60.5%
Balance sheet
7 models we track have a score here.
- 1
Gemini 3.1 Pro ↑3 83.4%
- 2 Claude Sonnet 5.5 ↓1 83.4%
- 3
Gemini 3.8 Flash 82.7%
- 4 Claude Opus 5.5 ↓2 82.3%
- 5 GPT-6 Sol 80.3%
- 6 GPT-6 Luna 80.1%
- 7 GPT-6 Astra 61.8%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Agentic Credit Analysis 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 Agentic Credit Analysis 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 (14 entries).
- Pass Models scored 7 models we track, plus 7 other entries on its leaderboard.
- Pass Newest score The newest is from September 2026, for Claude Sonnet 5.5.
- Pass Frontier models 3 of the top 10 have a score, led by GPT-6 Astra (#4).
- Pass Headroom The best is 80.2%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on builders.ramp.com: 14 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.