Papers › MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for...

MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI

27 Nov 2023CVPR 2024 1arXiv:2311.16502archive 2025-07-28

Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, Cong Wei, Botao Yu, Ruibin Yuan, Renliang Sun, Ming Yin, Boyuan Zheng, Zhenzhu Yang, Yibo Liu, Wenhao Huang, Huan Sun, Yu Su, Wenhu Chen

We introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU includes 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering. These questions span 30 subjects and 183 subfields, comprising 30 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures. Unlike existing benchmarks, MMMU focuses on advanced perception and reasoning with domain-specific knowledge, challenging models to perform tasks akin to those faced by experts. The evaluation of 14 open-source LMMs as well as the proprietary GPT-4V(ision) and Gemini highlights the substantial challenges posed by MMMU. Even the advanced GPT-4V and Gemini Ultra only achieve accuracies of 56% and 59% respectively, indicating significant room for improvement. We believe MMMU will stimulate the community to build next-generation multimodal foundation models towards expert artificial general intelligence.

PaperPDFConference PDFCodeCode 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 14 code samples: 13 from 3 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 14: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 2 ran (1 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 11 samples from 2 repositories, 10 ran (7 with no instrument failure; 3 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 13 samples that ran have no recorded date.

MMMU-Benchmark/MMMU officialmentioned on GitHubSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
01-ai/yi mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Yi: Open Foundation Models by 01.AI (arXiv:2403.04652; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified) and Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to... (arXiv:2403.14112; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
eric-ai-lab/probmed mentioned on GitHubpytorchMITSyntology: 6 samples, 5 ran (3 instrument-failed) · 1 unverified report
leloykun/mmfm-challenge mentioned on GitHubMITSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
opendatalab/pm4bench mentioned on GitHubApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark (arXiv:2409.02813; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

14 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 5 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.

1ran · honoured contract
5ran · our draft was wrong
7ran
1unverified

Licence: 2 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “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.

MMMU-Benchmark/MMMU official repository 2 samples, 2 ran (1 instrument-failed) · 0 unverified
mmmu_aggregate_results mmmu-pro/evaluate.py ran · honoured contract Apache-2.0 (permissive) · 15b4072238264b35 · report fixture: signature results:list/1/dict · returned float · level recorded 2026-09-22
mmmu_process_results mmmu-pro/evaluate.py ran · our draft was wrong Apache-2.0 (permissive) · 9073174a2f7541e1 · report fixture: signature results:dict/0/? · returned dict · level recorded 2026-09-22
eric-ai-lab/probmed community (archive-listed) 6 samples, 5 ran (3 instrument-failed) · 1 unverified
get_chunk in 197 papers eval/inference/CheXagent/model_vqa_med.py ran · our draft was wrong fingerprinted MIT (permissive) · 42a46570620cd9fa · report fixture: signature lst:list/1/int, n:int/0/int, k:int/0/int · returned list · level recorded, date not recorded
get_score_binary eval/calculate_score.py ran fingerprinted MIT (permissive) · dd2399dba3853e37 · report fixture: signature response:str/0/str, ans:str/0/str · returned int · level recorded 2026-09-25
get_score_dict eval/calculate_score.py ran MIT (permissive) · e738c5a0630373d4 · report fixture: signature response_data:list/1/dict, get_score:callable/0/? · returned defaultdict · level recorded 2026-09-24
local_image_to_data_url in 9 papers eval/inference/GPT-4V/gpt4v.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 829b3a29017bf6be · report fixture: signature image_path:str/0/str · returned str · level recorded 2026-09-24
split_list in 223 papers eval/inference/CheXagent/model_vqa_med.py ran · our draft was wrong fingerprinted MIT (permissive) · 076c252c52cbb161 · report fixture: signature lst:list/1/int, n:int/0/int · returned list · level recorded, date not recorded
parse_response in 39 papers eval/calculate_score.py unverified MIT (permissive) · eabb48a101284727 · report
leloykun/mmfm-challenge community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
LLM_eval eval_only_mixtral.py ran MIT (permissive) · c532e9d553008b9c · report fixture: signature model_id:str/0/str, model:callable/0/?, tokenizer:callable/0/?, batch_size:int/0/int, samples:list/1/dict, cuda:bool/0/bool · returned tuple · level recorded 2026-09-24
calculate_ins_level_score eval_only_mixtral.py ran MIT (permissive) · 30a511ce9cda0b48 · report fixture: signature results:dict/0/? · returned int · level recorded 2026-09-24
conv2sample eval_llava.py ran MIT (permissive) · d5c39813441ad22e · report fixture: signature args:Args/0/?, convs:list/1/dict, id:int/0/int, ds:str/0/str, image:str/0/str, _shots:NoneType/0/?, load_image:bool/0/bool · returned list · level recorded 2026-09-25
creat_prompt eval_only_mixtral.py ran MIT (permissive) · 433752319ee12f66 · report fixture: signature model_id:str/0/str, tokenizer:StandInTokenizer/0/?, question:str/0/str, answer:str/0/str, pred:str/0/str · returned str · level recorded 2026-09-24
get_category_name eval_only.py ran MIT (permissive) · fc1c84f0076beee4 · report fixture: signature data_id:str/0/str · returned str · level recorded 2026-09-24
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
extract_subset_name repository not located ran · our draft was wrong licence of this copy not recorded · 3f432bd90d038227 · report fixture: signature input_string:str/0/str · returned str · level recorded 2026-09-22

Tasks

Complex Query AnsweringLogical ReasoningVisual Reasoning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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