QuantEval
Models answer quantitative finance questions, solve mathematical problems, and implement trading strategies. The authors report answer accuracy and test the generated code.
- Made by
- Zhaolu Kang and colleagues
- Released
- January 2026
- Kind
- Finance
- Level
- University
- Scored
- Checked automatically
- Answers
- Code
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Law and finance
- Strongest model tested
- GPT-5 #71 on the capability index
- Last model added
- September 2025
- Scores refreshed
- November 20th, 2026
Claude Sonnet 4.5 leads with 86% among models released by September 2025 Claude Sonnet 4.5 leads with 86% among models released by September 2025
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score, so this is the Knowledge QA accuracy with chain of thought, its first ranked measure. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in September 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
- 86.0 Claude Sonnet 4.5
- 83.9 GPT-5
- 75.9
Qwen3-14B
- 66.7 Gemini 2.5 Pro (snapshot unspecified)
- 66.7
DeepSeek-R1-Distill-Qwen-14B
- 65.5
Qwen3-8B
- 64.4
Qwen3-4B
- 52.7 DeepSeek-R1-671B
- 50.6 DeepSeek-R1-Distill-Llama-8B
- 50.3 DianJin-R1-7B
- 48.5
Qwen3-30B-A3B
- 42.5
DeepSeek-R1-Distill-Qwen-7B
- 37.2
DeepSeek-R1-Distill-Qwen-1.5B
- 1 Claude Sonnet 4.5 86%
- 2 GPT-5 83.9%
- 3
Qwen3-14B 75.9%
- 4 Gemini 2.5 Pro (snapshot unspecified) 66.7%
- 5
DeepSeek-R1-Distill-Qwen-14B 66.7%
- 6
Qwen3-8B 65.5%
- 7
Qwen3-4B 64.4%
- 8 DeepSeek-R1-671B 52.7%
- 9 DeepSeek-R1-Distill-Llama-8B 50.6%
- 10 DianJin-R1-7B 50.3%
- 11
Qwen3-30B-A3B 48.5%
- 12
DeepSeek-R1-Distill-Qwen-7B 42.5%
- 13
DeepSeek-R1-Distill-Qwen-1.5B 37.2%
Source: The QuantEval paper
- 1 Claude Sonnet 4.5 86%
- 2 GPT-5 83.9%
- 3
Qwen3-14B 75.9%
- 4
DeepSeek-R1-Distill-Qwen-14B 66.7%
- 5
Qwen3-8B 65.5%
- 6
Qwen3-4B 64.4%
- 7
Qwen3-30B-A3B 48.5%
- 8
DeepSeek-R1-Distill-Qwen-7B 42.5%
- 9
DeepSeek-R1-Distill-Qwen-1.5B 37.2%
Source: The QuantEval paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 86% | Sep 2025 | Official leaderboard | |
| 2 | GPT-5 | 83.9% | Aug 2025 | Official leaderboard | |
| 3 | | 75.9% | Apr 2025 | Official leaderboard | |
| 4 | Gemini 2.5 Pro (snapshot unspecified) | 66.7% | Official leaderboard | ||
| 5 | | 66.7% | Jan 2025 | Official leaderboard | |
| 6 | | 65.5% | Apr 2025 | Official leaderboard | |
| 7 | | 64.4% | Apr 2025 | Official leaderboard | |
| 8 | DeepSeek-R1-671B | 52.7% | Official leaderboard | ||
| 9 | DeepSeek-R1-Distill-Llama-8B | 50.6% | Official leaderboard | ||
| 10 | DianJin-R1-7B | 50.3% | Official leaderboard | ||
| 11 | | 48.5% | Apr 2025 | Official leaderboard | |
| 12 | | 42.5% | Jan 2025 | Official leaderboard | |
| 13 | | 37.2% | Jan 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 86% | Sep 2025 | Official leaderboard | |
| 2 | GPT-5 | 83.9% | Aug 2025 | Official leaderboard | |
| 3 | | 75.9% | Apr 2025 | Official leaderboard | |
| 4 | | 66.7% | Jan 2025 | Official leaderboard | |
| 5 | | 65.5% | Apr 2025 | Official leaderboard | |
| 6 | | 64.4% | Apr 2025 | Official leaderboard | |
| 7 | | 48.5% | Apr 2025 | Official leaderboard | |
| 8 | | 42.5% | Jan 2025 | Official leaderboard | |
| 9 | | 37.2% | Jan 2025 | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s paper: Knowledge QA accuracy and Reasoning accuracy. Each ranks models on one part of the test. Claude Sonnet 4.5 leads Knowledge QA accuracy and GPT-5 leads Reasoning accuracy. Arrows show how far a model moved from its overall rank among the models we track.
Knowledge QA accuracy
9 models we track have a score here.
- 1 Claude Sonnet 4.5 86%
- 2 GPT-5 83.9%
- 3
Qwen3-14B 75.9%
- 4
DeepSeek-R1-Distill-Qwen-14B 66.7%
- 5
Qwen3-8B 65.5%
- 6
Qwen3-4B 64.4%
- 7
Qwen3-30B-A3B 48.5%
- 8
DeepSeek-R1-Distill-Qwen-7B 42.5%
- 9
DeepSeek-R1-Distill-Qwen-1.5B 37.2%
Reasoning accuracy
9 models we track have a score here.
- 1 GPT-5 ↑1 55%
- 2 Claude Sonnet 4.5 ↓1 43.1%
- 3
Qwen3-30B-A3B ↑4 40.5%
- 4
Qwen3-14B ↓1 35.4%
- 5
Qwen3-8B 33.9%
- 6
DeepSeek-R1-Distill-Qwen-1.5B ↑3 30%
- 7
DeepSeek-R1-Distill-Qwen-14B ↓3 29.2%
- 8
Qwen3-4B ↓2 27.7%
- 9
DeepSeek-R1-Distill-Qwen-7B ↓1 21.5%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The QuantEval paper
Claude Sonnet 4.5 on the official leaderboard passed 85% in September 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 QuantEval 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
7 of 8 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark
Catalog record 1 warning 1 pass
- Warning Task access We don’t know whether the tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (13 entries).
- Pass Models scored 9 models we track, plus 4 other entries on its leaderboard.
- Note Newest score The newest came 14 months ago, in September 2025, for Claude Sonnet 4.5. 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 (#71).
- Note Headroom Saturated. The best is 86%, past 85% since September 2025.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 9 rows for models we track and 4 other entries 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.