FinMaster
Models complete financial workflows using simulated company records. The benchmark includes single calculations and tasks that require several financial metrics.
- Made by
- Junzhe Jiang and colleagues
- Released
- May 2025
- Kind
- Finance
- Level
- University
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Subject
- Economics and business
- Language
- English
- Interaction
- Single turn
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Law and finance
- Strongest model tested
- Claude 3.7 Sonnet #119 on the capability index
- Last model added
- April 2025
- Scores refreshed
- November 20th, 2026
o3-mini leads with 73% among models released by April 2025
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 April 2025, 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
- 1 o3-mini reasoning 73%
- 2 Claude 3.7 Sonnet non-reasoning 72%
- 3
DeepSeek-V3 Mar 2025, non-reasoning 70%
- 4 GPT-4.1 non-reasoning 62%
- 5 GPT-4.1 mini non-reasoning 58%
- 6 GPT-4o mini non-reasoning 46%
- 7 GPT-4.1 nano non-reasoning 40%
Source: Official FinMaster leaderboard
| # | Model | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | o3-mini | 73% | reasoning | Jan 2025 | openai.com | Official leaderboard |
| 2 | Claude 3.7 Sonnet | 72% | non-reasoning | Feb 2025 | anthropic.com | Official leaderboard |
| 3 | | 70% | non-reasoning | Mar 2025 | api-docs.deepseek.com | Official leaderboard |
| 4 | GPT-4.1 | 62% | non-reasoning | Apr 2025 | openai.com | Official leaderboard |
| 5 | GPT-4.1 mini | 58% | non-reasoning | Apr 2025 | platform.openai.com | Official leaderboard |
| 6 | GPT-4o mini | 46% | non-reasoning | Jul 2024 | openai.com | Official leaderboard |
| 7 | GPT-4.1 nano | 40% | non-reasoning | Apr 2025 | platform.openai.com | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Financial Literacy, Accounting and Auditing. o3-mini leads 3 of them, and Claude 3.7 Sonnet leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Financial Literacy
7 models we track have a score here.
- 1 o3-mini 100%
- 2 Claude 3.7 Sonnet 100%
- 3 GPT-4.1 ↑1 100%
- 4
DeepSeek-V3 Mar 2025 ↓1 99%
- 5 GPT-4.1 mini 90%
- 6 GPT-4o mini 89%
- 7 GPT-4.1 nano 85%
Accounting
7 models we track have a score here.
- 1 o3-mini 35%
- 2 GPT-4.1 ↑2 33%
- 3 Claude 3.7 Sonnet ↓1 30%
- 4
DeepSeek-V3 Mar 2025 ↓1 21%
- 5 GPT-4.1 mini 20%
- 6 GPT-4o mini 8.00%
- 7 GPT-4.1 nano 4.00%
Auditing
7 models we track have a score here.
- 1 o3-mini 85%
- 2 Claude 3.7 Sonnet 70%
- 3
DeepSeek-V3 Mar 2025 69%
- 4 GPT-4.1 41%
- 5 GPT-4.1 mini 29%
- 6 GPT-4o mini 27%
- 7 GPT-4.1 nano 0%
Consulting
7 models we track have a score here.
- 1 Claude 3.7 Sonnet ↑1 80%
- 2
DeepSeek-V3 Mar 2025 ↑1 80%
- 3 o3-mini ↓2 66%
- 4 GPT-4.1 mini ↑1 66%
- 5 GPT-4.1 ↓1 56%
- 6 GPT-4.1 nano ↑1 42%
- 7 GPT-4o mini ↓1 37%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official FinMaster 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 FinMaster 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
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 19 months ago, in April 2025, for GPT-4.1. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the official leaderboard (7 entries).
- Pass Models scored 7 models we track.
- Warning Newest score The newest came 19 months ago, in April 2025, for GPT-4.1.
- Note Frontier models None of the top 10 has a score. The strongest tested is Claude 3.7 Sonnet (#119).
- Pass Headroom The best is 73%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on jianginsight.github.io: 7 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.