Papers › ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models

ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models

21 Sep 2024arXiv:2409.13989archive 2025-07-28

Yuqing Huang, Rongyang Zhang, Xuesong He, Xuyang Zhi, Hao Wang, Xin Li, Feiyang Xu, Deguang Liu, Huadong Liang, Yi Li, Jian Cui, Zimu Liu, Shijin Wang, Guoping Hu, Guiquan Liu, Qi Liu, Defu Lian, Enhong Chen

There is a growing interest in the role that LLMs play in chemistry which lead to an increased focus on the development of LLMs benchmarks tailored to chemical domains to assess the performance of LLMs across a spectrum of chemical tasks varying in type and complexity. However, existing benchmarks in this domain fail to adequately meet the specific requirements of chemical research professionals. To this end, we propose ChemEval, which provides a comprehensive assessment of the capabilities of LLMs across a wide range of chemical domain tasks. Specifically, ChemEval identified 4 crucial progressive levels in chemistry, assessing 12 dimensions of LLMs across 42 distinct chemical tasks which are informed by open-source data and the data meticulously crafted by chemical experts, ensuring that the tasks have practical value and can effectively evaluate the capabilities of LLMs. In the experiment, we evaluate 12 mainstream LLMs on ChemEval under zero-shot and few-shot learning contexts, which included carefully selected demonstration examples and carefully designed prompts. The results show that while general LLMs like GPT-4 and Claude-3.5 excel in literature understanding and instruction following, they fall short in tasks demanding advanced chemical knowledge. Conversely, specialized LLMs exhibit enhanced chemical competencies, albeit with reduced literary comprehension. This suggests that LLMs have significant potential for enhancement when tackling sophisticated tasks in the field of chemistry. We believe our work will facilitate the exploration of their potential to drive progress in chemistry. Our benchmark and analysis will be available at { https://github.com/USTC-StarTeam/ChemEval}.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 18 code samples harvested from 1 repository linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 2 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 17 ran (7 with no instrument failure; 10 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ustc-starteam/chemeval officialmentioned in paperNOASSERTIONSyntology: 18 samples, 17 ran (10 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

18 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 2 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
2ran · violated contract
10ran · our draft was wrong
1ran
1unverified

Licence: 18 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ustc-starteam/chemeval. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

ustc-starteam/chemeval official repository 18 samples, 17 ran (10 instrument-failed) · 1 unverified
calculate_accuracy in 65 papers Multimodel/3_code_evaluate/classification.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 38af2d0c0f3866ae · report fixture: signature gold_label_list:list/1/str, pred_label_list:list/1/str · returned tuple · level recorded 2026-09-24
calculate_accuracy in 65 papers Multimodel/3_code_evaluate/entity_extraction.py ran licence not identified · pointer only · 4663d9d3a8c44ca0 · report fixture: signature golds:list/1/str, pres:list/1/str · returned float · level recorded 2026-09-24
calculate_accuracy in 65 papers Multimodel/3_code_evaluate/entity_recognition.py ran · honoured contract licence not identified · pointer only · 52a5bf0190d24222 · report fixture: signature jsonl_file:str/0/str · returned float · level recorded 2026-09-24
calculate_accuracy2 Multimodel/3_code_evaluate/classification.py ran · our draft was wrong fingerprinted licence not identified · pointer only · bbcdf4700d65e7a7 · report fixture: signature gold_label_list:list/1/str, pred_label_list:list/1/str · returned tuple · level recorded 2026-09-24
calculate_f1_score in 14 papers Multimodel/3_code_evaluate/entity_extraction.py ran · honoured contract fingerprinted licence not identified · pointer only · f16aa628189064dd · report fixture: signature true_entities:str/0/str, predicted_entities:str/0/str · returned float · level recorded 2026-09-24
calculate_overlap Multimodel/3_code_evaluate/Reaction_Rate_Prediction.py ran · honoured contract licence not identified · pointer only · 4c5ae6c63f9d3191 · report fixture: signature range_dict:dict/0/? · returned float · level recorded 2026-09-24
convert_jsonl_to_json Multimodel/3_code_evaluate/Reaction_Rate_Prediction.py ran · our draft was wrong licence not identified · pointer only · 642c8443ad29a0ac · report fixture: signature jsonl_file_path:str/0/str · returned list · level recorded 2026-09-24
convert_jsonl_to_json Multimodel/3_code_evaluate/entity_recognition.py ran · our draft was wrong licence not identified · pointer only · 9dee189876cd68bb · report fixture: signature jsonl_file_path:str/0/str · returned list · level recorded 2026-09-24
find_last_ABCD_letter Multimodel/3_code_evaluate/1Extract.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 81608657e54f18aa · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-24
is_valid_dict_format Multimodel/3_code_evaluate/1Extract.py ran · violated contract licence not identified · pointer only · fd13808c01c5b673 · report fixture: signature s:str/0/str · returned bool · level recorded 2026-09-24
judge_string_exact_match Multimodel/3_code_evaluate/molecule_design_F.py ran · violated contract licence not identified · pointer only · 11bf4f54be9fdc78 · report fixture: signature pred_string_list:list/1/str, golds_string_list:list/1/list · returned ndarray · level recorded 2026-09-24
list_json_files Multimodel/3_code_evaluate/entity_extraction.py ran · our draft was wrong licence not identified · pointer only · 36da7984e994b6a6 · report fixture: signature folder_path:str/0/str · returned list · level recorded 2026-09-24
list_json_files Multimodel/3_code_evaluate/jiping.py ran · our draft was wrong licence not identified · pointer only · a4f79ce313cb53e8 · report fixture: signature folder_path:str/0/str · returned list · level recorded 2026-09-24
parse_molecular_formula Multimodel/3_code_evaluate/molecule_design_F.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 3de6691c44027248 · report fixture: signature formula:str/0/str · returned dict · level recorded 2026-09-24
parse_range in 22 papers Multimodel/3_code_evaluate/Reaction_Rate_Prediction.py ran · honoured contract fingerprinted licence not identified · pointer only · 696f6c48ae39eef8 · report fixture: signature range_str:str/0/str · returned tuple · level recorded 2026-09-24
re_formers_Lla Multimodel/3_code_evaluate/molecule_design.py ran · our draft was wrong fingerprinted licence not identified · pointer only · aa3f745fb79488a6 · report fixture: signature string:str/0/str · returned str · level recorded 2026-09-24
read_file in 112 papers Multimodel/3_code_evaluate/1Extract.py ran · our draft was wrong licence not identified · pointer only · d23978079d307710 · report fixture: signature file_path:str/0/str · returned tuple · level recorded 2026-09-24
calculate_formula_metrics Multimodel/3_code_evaluate/molecule_design_F.py unverified licence not identified · pointer only · df1cc9c9fcde4f32 · report

Tasks

Few-Shot LearningInstruction Following

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutFocusGPT-4Label SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections