SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.12659 · 2024

FinBen: A Holistic Financial Benchmark for Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

8 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 3 violated it and 0 have no contract verdict; 5 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.12659.json · badge: /api/ran/2402.12659.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
chancefocus/pixiu canonical (classifier label)
classifier basis: census
8 ran · 4 no recorded run
FunctionStatusWhere it lives
best_demos Ran
ran; our contract draft was wrong, not the code
chancefocus/pixiu/src/factscore_package/atomic_facts.py
pointer only (licence: MIT); the stored copy get_code serves, from dmis-lab/olaph, is pointer only (licence: NONE) · get_code("510528f4db1006bc")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from dmis-lab/olaph, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

is_invalid_paragraph_ppl Ran
ran, violated the contract we drafted
chancefocus/pixiu/src/factscore_package/abstain_detection.py
pointer only (licence: MIT); the stored copy get_code serves, from dmis-lab/olaph, is pointer only (licence: NONE) · get_code("8eb846a8e76a79b8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from dmis-lab/olaph, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

is_invalid_ppl Ran
ran, violated the contract we drafted
chancefocus/pixiu/src/factscore_package/abstain_detection.py
pointer only (licence: MIT); the stored copy get_code serves, from dmis-lab/olaph, is pointer only (licence: NONE) · get_code("672bd38d830be48d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from dmis-lab/olaph, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normalize_answer Ran
ran; our contract draft was wrong, not the code
chancefocus/pixiu/src/factscore_package/atomic_facts.py
pointer only (licence: MIT); the stored copy get_code serves, from saptarshi059/cdqa-project, is pointer only (licence: NONE) · get_code("6a96435eba311b08")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from saptarshi059/cdqa-project, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

remove_citation Ran
ran; our contract draft was wrong, not the code
chancefocus/pixiu/src/factscore_package/abstain_detection.py
pointer only (licence: MIT); the stored copy get_code serves, from rhyang2021/logu, is pointer only (licence: NONE) · get_code("3635046105ae0fce")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from rhyang2021/logu, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

single_chat Ran
ran; our contract draft was wrong, not the code
chancefocus/pixiu/src/chatlm.py
code served (permissive licence) · get_code("371e5c4f5d2d78ca")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned coroutine. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import asyncio
from unittest.mock import AsyncMock, MagicMock

# Create a mock client that simulates the API response
mock_client = AsyncMock()

# Create a mock response object with the expected structure
mock_response = MagicMock()
mock_response.json.return_value = {
    'choices': [
        {
            'message': {
                'content': 'This is a test response from the API.'
            }
        }
    ]
}

# Set up the client to return the mock response
mock_client.post = AsyncMock(return_value=mock_response)

# Define the kwargs that would be passed to client.post
kwargs = {
    'messages': [
        {'role': 'user', 'content': 'Hello, how are you?'}
    ],
    'model': 'gpt-3.5-turbo',
    'temperature': 0.7
}

# Construct the ARGS dictionary with all parameters
ARGS = {
    'client': mock_client,
    'kwargs': kwargs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type coroutine — a coroutine output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a coroutine output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
softmax Ran
ran, violated the contract we drafted
chancefocus/pixiu/src/factscore_package/npm.py
code served (permissive licence) · get_code("925c59b7e44138ab")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (4,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# The softmax function takes a single parameter 'x' which should be a numpy array
# The function computes exp(x - max(x)) / sum(exp(x - max(x)))
# So x needs to be a 1D or 2D numpy array of numeric values

x = np.array([1.0, 2.0, 3.0, 4.0])

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (4,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
text_to_sentences Ran
ran; our contract draft was wrong, not the code
chancefocus/pixiu/src/factscore_package/atomic_facts.py
pointer only (licence: MIT); the stored copy get_code serves, from dmis-lab/olaph, is pointer only (licence: NONE) · get_code("13867f872a481bd3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from dmis-lab/olaph, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

evaluate Not yet run
unverified (harvested, no recorded run)
chancefocus/pixiu/src/interface.py
code served (permissive licence) · get_code("5a6e0b41ccbd8a98")
How it ran

no invocation recorded.

generate_prompt Not yet run
unverified (harvested, no recorded run)
chancefocus/pixiu/src/interface.py
code served (permissive licence) · get_code("d8c48497dd9cc819")
How it ran

no invocation recorded.

make_table Not yet run
unverified (harvested, no recorded run)
chancefocus/pixiu/src/evaluator.py
pointer only (licence: MIT); the stored copy get_code serves, from princeton-nlp/QuRating, is pointer only (licence: NONE) · get_code("9d95c14130837ee4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from princeton-nlp/QuRating, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

recover_instruct_llama Not yet run
unverified (harvested, no recorded run)
chancefocus/pixiu/src/factscore_package/download_data.py
code served (permissive licence) · get_code("a643d9a7436e58c2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 12 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 9 the same month, 9 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
normalize_answer 37 other papers
25 dated earlier, 1 the same month, 11 later · 1 only as an assembly brick
1808.07042 (2018-08)
CoQA: A Conversational Question Answering Challenge
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1902.01718 (2019-02)
End-to-End Open-Domain Question Answering with BERTserini
and 34 more not named here
make_table 9 other papers
4 dated earlier, 3 the same month, 2 later
2303.17003 (2023-03)
Evaluating GPT-3.5 and GPT-4 Models on Brazilian University Admission Exams
2305.14493 (2023-05)
Do prompt positions really matter?
2307.16039 (2023-07)
Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback
and 6 more not named here
is_invalid_paragraph_ppl 6 other papers
1 dated earlier, 1 the same month, 4 later
2305.14251 (2023-05)
FACTSCORE: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
2402.18045 (2024-02)
Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore
2403.03823 (2024-03)
A Modular Approach for Multimodal Summarization of TV Shows
and 3 more not named here
is_invalid_ppl 6 other papers
1 dated earlier, 1 the same month, 4 later
2305.14251 (2023-05)
FACTSCORE: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
2402.18045 (2024-02)
Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore
2403.03823 (2024-03)
A Modular Approach for Multimodal Summarization of TV Shows
and 3 more not named here
remove_citation 6 other papers
1 dated earlier, 1 the same month, 4 later
2305.14251 (2023-05)
FACTSCORE: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
2402.18045 (2024-02)
Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore
2403.03823 (2024-03)
A Modular Approach for Multimodal Summarization of TV Shows
and 3 more not named here
best_demos 5 other papers
1 dated earlier, 1 the same month, 3 later
2305.14251 (2023-05)
FACTSCORE: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
2402.18045 (2024-02)
Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore
2403.03823 (2024-03)
A Modular Approach for Multimodal Summarization of TV Shows
and 2 more not named here
text_to_sentences 5 other papers
1 dated earlier, 1 the same month, 3 later
2305.14251 (2023-05)
FACTSCORE: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
2402.18045 (2024-02)
Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore
2403.03823 (2024-03)
A Modular Approach for Multimodal Summarization of TV Shows
and 2 more not named here
recover_instruct_llama 4 other papers
1 dated earlier, 1 the same month, 2 later
2305.14251 (2023-05)
FACTSCORE: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
2402.18045 (2024-02)
Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore
2403.03823 (2024-03)
A Modular Approach for Multimodal Summarization of TV Shows
and 1 more not named here
softmax 3 other papers
1 dated earlier, 1 the same month, 1 later
2305.14251 (2023-05)
FACTSCORE: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
2402.18045 (2024-02)
Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore
2403.03823 (2024-03)
A Modular Approach for Multimodal Summarization of TV Shows
evaluate 1 other paper
1 dated earlier
2310.05620 (2023-10)
LAiW: A Chinese Legal Large Language Models Benchmark
generate_prompt 1 other paper
1 dated earlier
2310.05620 (2023-10)
LAiW: A Chinese Legal Large Language Models Benchmark
single_chat 1 other paper
1 dated earlier
2306.05443 (2023-06)
PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

LLMs have transformed NLP and shown promise in various fields, yet their potential in finance is underexplored due to a lack of comprehensive evaluation benchmarks, the rapid development of LLMs, and the complexity of financial tasks. In this paper, we introduce FinBen, the first extensive open-source evaluation benchmark, including 36 datasets spanning 24 financial tasks, covering seven critical aspects: information extraction (IE), textual analysis, question answering (QA), text generation, risk management, forecasting, and decision-making. FinBen offers several key innovations: a broader range of tasks and datasets, the first evaluation of stock trading, novel agent and Retrieval-Augmented Generation (RAG) evaluation, and three novel open-source evaluation datasets for text summarization, question answering, and stock trading. Our evaluation of 15 representative LLMs, including GPT-4, ChatGPT, and the latest Gemini, reveals several key findings: While LLMs excel in IE and textual analysis, they struggle with advanced reasoning and complex tasks like text generation and forecasting. GPT-4 excels in IE and stock trading, while Gemini is better at text generation and forecasting. Instruction-tuned LLMs improve textual analysis but offer limited benefits for complex tasks such as QA. FinBen has been used to host the first financial LLMs shared task at the FinNLP-AgentScen workshop during IJCAI-2024, attracting 12 teams. Their novel solutions outperformed GPT-4, showcasing FinBen's potential to drive innovation in financial LLMs. All datasets, results, and codes are released for the research community: https://github.com/The-FinAI/PIXIU.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.12659")
get_code_for_paper("2402.12659")
have("2402.12659")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.12659.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.12659.svg)](https://syntology.ai/paper/2402.12659)

Connect an agent — have() is free.