SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models Article Swipe
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2307.10635
Most of the existing Large Language Model (LLM) benchmarks on scientific problem reasoning focus on problems grounded in high-school subjects and are confined to elementary algebraic operations. To systematically examine the reasoning capabilities required for solving complex scientific problems, we introduce an expansive benchmark suite SciBench for LLMs. SciBench contains a carefully curated dataset featuring a range of collegiate-level scientific problems from mathematics, chemistry, and physics domains. Based on the dataset, we conduct an in-depth benchmarking study of representative open-source and proprietary LLMs with various prompting strategies. The results reveal that the current LLMs fall short of delivering satisfactory performance, with the best overall score of merely 43.22%. Furthermore, through a detailed user study, we categorize the errors made by LLMs into ten problem-solving abilities. Our analysis indicates that no single prompting strategy significantly outperforms the others and some strategies that demonstrate improvements in certain problem-solving skills could result in declines in other skills. We envision that SciBench will catalyze further developments in the reasoning abilities of LLMs, thereby ultimately contributing to scientific research and discovery.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2307.10635
- https://arxiv.org/pdf/2307.10635
- OA Status
- green
- Cited By
- 16
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4385002382
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4385002382Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2307.10635Digital Object Identifier
- Title
-
SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language ModelsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-07-20Full publication date if available
- Authors
-
Xiaoxuan Wang, Ziniu Hu, Pan Lu, Yanqiao Zhu, Jieyu Zhang, Satyen Subramaniam, Arjun R. Loomba, Shichang Zhang, Yizhou Sun, Wei WangList of authors in order
- Landing page
-
https://arxiv.org/abs/2307.10635Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2307.10635Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2307.10635Direct OA link when available
- Concepts
-
Mathematics education, Computer science, Management science, Psychology, EngineeringTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
16Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 5, 2024: 7, 2023: 4Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4385002382 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2307.10635 |
| ids.doi | https://doi.org/10.48550/arxiv.2307.10635 |
| ids.openalex | https://openalex.org/W4385002382 |
| fwci | |
| type | preprint |
| title | SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11122 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.8654999732971191 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1706 |
| topics[0].subfield.display_name | Computer Science Applications |
| topics[0].display_name | Online Learning and Analytics |
| topics[1].id | https://openalex.org/T12887 |
| topics[1].field.id | https://openalex.org/fields/32 |
| topics[1].field.display_name | Psychology |
| topics[1].score | 0.8144999742507935 |
| topics[1].domain.id | https://openalex.org/domains/2 |
| topics[1].domain.display_name | Social Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/3204 |
| topics[1].subfield.display_name | Developmental and Educational Psychology |
| topics[1].display_name | Educational Strategies and Epistemologies |
| topics[2].id | https://openalex.org/T11715 |
| topics[2].field.id | https://openalex.org/fields/33 |
| topics[2].field.display_name | Social Sciences |
| topics[2].score | 0.7590000033378601 |
| topics[2].domain.id | https://openalex.org/domains/2 |
| topics[2].domain.display_name | Social Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/3304 |
| topics[2].subfield.display_name | Education |
| topics[2].display_name | Education and Critical Thinking Development |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C145420912 |
| concepts[0].level | 1 |
| concepts[0].score | 0.5475457906723022 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q853077 |
| concepts[0].display_name | Mathematics education |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.5022149085998535 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C539667460 |
| concepts[2].level | 1 |
| concepts[2].score | 0.3300822377204895 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q2414942 |
| concepts[2].display_name | Management science |
| concepts[3].id | https://openalex.org/C15744967 |
| concepts[3].level | 0 |
| concepts[3].score | 0.3045163154602051 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[3].display_name | Psychology |
| concepts[4].id | https://openalex.org/C127413603 |
| concepts[4].level | 0 |
| concepts[4].score | 0.12249097228050232 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[4].display_name | Engineering |
| keywords[0].id | https://openalex.org/keywords/mathematics-education |
| keywords[0].score | 0.5475457906723022 |
| keywords[0].display_name | Mathematics education |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.5022149085998535 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/management-science |
| keywords[2].score | 0.3300822377204895 |
| keywords[2].display_name | Management science |
| keywords[3].id | https://openalex.org/keywords/psychology |
| keywords[3].score | 0.3045163154602051 |
| keywords[3].display_name | Psychology |
| keywords[4].id | https://openalex.org/keywords/engineering |
| keywords[4].score | 0.12249097228050232 |
| keywords[4].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2307.10635 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2307.10635 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2307.10635 |
| locations[1].id | doi:10.48550/arxiv.2307.10635 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2307.10635 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100695917 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-0501-1521 |
| authorships[0].author.display_name | Xiaoxuan Wang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Wang, Xiaoxuan |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5114973490 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-4663-0166 |
| authorships[1].author.display_name | Ziniu Hu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Hu, Ziniu |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100610327 |
| authorships[2].author.orcid | https://orcid.org/0009-0000-2025-9528 |
| authorships[2].author.display_name | Pan Lu |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Lu, Pan |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5015101640 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-2205-5304 |
| authorships[3].author.display_name | Yanqiao Zhu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Zhu, Yanqiao |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5017743340 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-2827-3487 |
| authorships[4].author.display_name | Jieyu Zhang |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Zhang, Jieyu |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5104146192 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Satyen Subramaniam |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Subramaniam, Satyen |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5111012173 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Arjun R. Loomba |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Loomba, Arjun R. |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5101412767 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-5850-4928 |
| authorships[7].author.display_name | Shichang Zhang |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Zhang, Shichang |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5025213473 |
| authorships[8].author.orcid | https://orcid.org/0000-0003-1812-6843 |
| authorships[8].author.display_name | Yizhou Sun |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Sun, Yizhou |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5091610270 |
| authorships[9].author.orcid | |
| authorships[9].author.display_name | Wei Wang |
| authorships[9].author_position | last |
| authorships[9].raw_author_name | Wang, Wei |
| authorships[9].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2307.10635 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2023-07-22T00:00:00 |
| display_name | SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11122 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.8654999732971191 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1706 |
| primary_topic.subfield.display_name | Computer Science Applications |
| primary_topic.display_name | Online Learning and Analytics |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W2358668433, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W2382290278, https://openalex.org/W2478288626, https://openalex.org/W4391913857, https://openalex.org/W2350741829 |
| cited_by_count | 16 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 5 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 7 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 4 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2307.10635 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2307.10635 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2307.10635 |
| primary_location.id | pmh:oai:arXiv.org:2307.10635 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2307.10635 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2307.10635 |
| publication_date | 2023-07-20 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 50, 55, 110 |
| abstract_inverted_index.To | 27 |
| abstract_inverted_index.We | 154 |
| abstract_inverted_index.an | 41, 73 |
| abstract_inverted_index.by | 119 |
| abstract_inverted_index.in | 17, 143, 149, 151, 162 |
| abstract_inverted_index.no | 129 |
| abstract_inverted_index.of | 1, 57, 77, 96, 105, 166 |
| abstract_inverted_index.on | 9, 14, 68 |
| abstract_inverted_index.to | 23, 171 |
| abstract_inverted_index.we | 39, 71, 114 |
| abstract_inverted_index.Our | 125 |
| abstract_inverted_index.The | 87 |
| abstract_inverted_index.and | 20, 64, 80, 137, 174 |
| abstract_inverted_index.are | 21 |
| abstract_inverted_index.for | 34, 46 |
| abstract_inverted_index.ten | 122 |
| abstract_inverted_index.the | 2, 30, 69, 91, 101, 116, 135, 163 |
| abstract_inverted_index.LLMs | 82, 93, 120 |
| abstract_inverted_index.Most | 0 |
| abstract_inverted_index.best | 102 |
| abstract_inverted_index.fall | 94 |
| abstract_inverted_index.from | 61 |
| abstract_inverted_index.into | 121 |
| abstract_inverted_index.made | 118 |
| abstract_inverted_index.some | 138 |
| abstract_inverted_index.that | 90, 128, 140, 156 |
| abstract_inverted_index.user | 112 |
| abstract_inverted_index.will | 158 |
| abstract_inverted_index.with | 83, 100 |
| abstract_inverted_index.(LLM) | 7 |
| abstract_inverted_index.Based | 67 |
| abstract_inverted_index.LLMs, | 167 |
| abstract_inverted_index.LLMs. | 47 |
| abstract_inverted_index.Large | 4 |
| abstract_inverted_index.Model | 6 |
| abstract_inverted_index.could | 147 |
| abstract_inverted_index.focus | 13 |
| abstract_inverted_index.other | 152 |
| abstract_inverted_index.range | 56 |
| abstract_inverted_index.score | 104 |
| abstract_inverted_index.short | 95 |
| abstract_inverted_index.study | 76 |
| abstract_inverted_index.suite | 44 |
| abstract_inverted_index.errors | 117 |
| abstract_inverted_index.merely | 106 |
| abstract_inverted_index.others | 136 |
| abstract_inverted_index.result | 148 |
| abstract_inverted_index.reveal | 89 |
| abstract_inverted_index.single | 130 |
| abstract_inverted_index.skills | 146 |
| abstract_inverted_index.study, | 113 |
| abstract_inverted_index.43.22%. | 107 |
| abstract_inverted_index.certain | 144 |
| abstract_inverted_index.complex | 36 |
| abstract_inverted_index.conduct | 72 |
| abstract_inverted_index.curated | 52 |
| abstract_inverted_index.current | 92 |
| abstract_inverted_index.dataset | 53 |
| abstract_inverted_index.examine | 29 |
| abstract_inverted_index.further | 160 |
| abstract_inverted_index.overall | 103 |
| abstract_inverted_index.physics | 65 |
| abstract_inverted_index.problem | 11 |
| abstract_inverted_index.results | 88 |
| abstract_inverted_index.skills. | 153 |
| abstract_inverted_index.solving | 35 |
| abstract_inverted_index.thereby | 168 |
| abstract_inverted_index.through | 109 |
| abstract_inverted_index.various | 84 |
| abstract_inverted_index.Language | 5 |
| abstract_inverted_index.SciBench | 45, 48, 157 |
| abstract_inverted_index.analysis | 126 |
| abstract_inverted_index.catalyze | 159 |
| abstract_inverted_index.confined | 22 |
| abstract_inverted_index.contains | 49 |
| abstract_inverted_index.dataset, | 70 |
| abstract_inverted_index.declines | 150 |
| abstract_inverted_index.detailed | 111 |
| abstract_inverted_index.domains. | 66 |
| abstract_inverted_index.envision | 155 |
| abstract_inverted_index.existing | 3 |
| abstract_inverted_index.grounded | 16 |
| abstract_inverted_index.in-depth | 74 |
| abstract_inverted_index.problems | 15, 60 |
| abstract_inverted_index.required | 33 |
| abstract_inverted_index.research | 173 |
| abstract_inverted_index.strategy | 132 |
| abstract_inverted_index.subjects | 19 |
| abstract_inverted_index.abilities | 165 |
| abstract_inverted_index.algebraic | 25 |
| abstract_inverted_index.benchmark | 43 |
| abstract_inverted_index.carefully | 51 |
| abstract_inverted_index.expansive | 42 |
| abstract_inverted_index.featuring | 54 |
| abstract_inverted_index.indicates | 127 |
| abstract_inverted_index.introduce | 40 |
| abstract_inverted_index.problems, | 38 |
| abstract_inverted_index.prompting | 85, 131 |
| abstract_inverted_index.reasoning | 12, 31, 164 |
| abstract_inverted_index.abilities. | 124 |
| abstract_inverted_index.benchmarks | 8 |
| abstract_inverted_index.categorize | 115 |
| abstract_inverted_index.chemistry, | 63 |
| abstract_inverted_index.delivering | 97 |
| abstract_inverted_index.discovery. | 175 |
| abstract_inverted_index.elementary | 24 |
| abstract_inverted_index.scientific | 10, 37, 59, 172 |
| abstract_inverted_index.strategies | 139 |
| abstract_inverted_index.ultimately | 169 |
| abstract_inverted_index.demonstrate | 141 |
| abstract_inverted_index.high-school | 18 |
| abstract_inverted_index.open-source | 79 |
| abstract_inverted_index.operations. | 26 |
| abstract_inverted_index.outperforms | 134 |
| abstract_inverted_index.proprietary | 81 |
| abstract_inverted_index.strategies. | 86 |
| abstract_inverted_index.Furthermore, | 108 |
| abstract_inverted_index.benchmarking | 75 |
| abstract_inverted_index.capabilities | 32 |
| abstract_inverted_index.contributing | 170 |
| abstract_inverted_index.developments | 161 |
| abstract_inverted_index.improvements | 142 |
| abstract_inverted_index.mathematics, | 62 |
| abstract_inverted_index.performance, | 99 |
| abstract_inverted_index.satisfactory | 98 |
| abstract_inverted_index.significantly | 133 |
| abstract_inverted_index.representative | 78 |
| abstract_inverted_index.systematically | 28 |
| abstract_inverted_index.problem-solving | 123, 145 |
| abstract_inverted_index.collegiate-level | 58 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 10 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.8600000143051147 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |