Papers › UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling

UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling

9 Aug 2024arXiv:2408.04810archive 2025-07-28

Haider Al-Tahan, Quentin Garrido, Randall Balestriero, Diane Bouchacourt, Caner Hazirbas, Mark Ibrahim

Significant research efforts have been made to scale and improve vision-language model (VLM) training approaches. Yet, with an ever-growing number of benchmarks, researchers are tasked with the heavy burden of implementing each protocol, bearing a non-trivial computational cost, and making sense of how all these benchmarks translate into meaningful axes of progress. To facilitate a systematic evaluation of VLM progress, we introduce UniBench: a unified implementation of 50+ VLM benchmarks spanning a comprehensive range of carefully categorized capabilities from object recognition to spatial awareness, counting, and much more. We showcase the utility of UniBench for measuring progress by evaluating nearly 60 publicly available vision-language models, trained on scales of up to 12.8B samples. We find that while scaling training data or model size can boost many vision-language model capabilities, scaling offers little benefit for reasoning or relations. Surprisingly, we also discover today's best VLMs struggle on simple digit recognition and counting tasks, e.g. MNIST, which much simpler networks can solve. Where scale falls short, we find that more precise interventions, such as data quality or tailored-learning objectives offer more promise. For practitioners, we also offer guidance on selecting a suitable VLM for a given application. Finally, we release an easy-to-run UniBench code-base with the full set of 50+ benchmarks and comparisons across 59 models as well as a distilled, representative set of benchmarks that runs in 5 minutes on a single GPU.

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 9 code samples harvested from 1 repository linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 5 ran (3 with no instrument failure; 2 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.

facebookresearch/unibench officialmentioned in papermentioned on GitHubjaxNOASSERTIONSyntology: 9 samples, 5 ran (2 instrument-failed) · 4 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

9 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 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.

2ran · our draft was wrong
3ran
4unverified

Licence: 9 of the 9 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 facebookresearch/unibench. “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.

facebookresearch/unibench official repository 9 samples, 5 ran (2 instrument-failed) · 4 unverified
df_to_table unibench/common_utils/utils.py ran licence not identified · pointer only · acb03ffc90c5d69e · report fixture: signature pandas_dataframe:DataFrame/0/?, rich_table:Table/0/?, show_index:bool/0/bool, index_name:str/0/str · returned Table · level recorded 2026-09-24
get_benchmark_info unibench/benchmarks_zoo/registry.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 157cbc5ff7648503 · report fixture: signature benchmark_name:str/0/str · returned defaultdict · level recorded 2026-09-24
get_model_info in 13 papers unibench/models_zoo/registry.py ran · our draft was wrong fingerprinted licence not identified · pointer only · ce4164ce34ef669f · report fixture: signature model_name:str/0/str · returned defaultdict · level recorded 2026-09-24
register_benchmark unibench/benchmarks_zoo/registry.py ran licence not identified · pointer only · 46d22fdff321711d · report fixture: signature names:str/0/str, info:dict/0/? · returned function · level recorded 2026-09-24
register_model in 68 papers unibench/models_zoo/registry.py ran licence not identified · pointer only · 443a61be3b02f5a2 · report fixture: signature frameworks:str/0/str, info:dict/0/? · returned function · level recorded 2026-09-24
get_benchmark_mappings unibench/common_utils/utils.py unverified licence not identified · pointer only · 44c30f2c1af83047 · report
get_model_mappings unibench/common_utils/utils.py unverified licence not identified · pointer only · c2855847e2b846d7 · report
load_benchmark in 6 papers unibench/benchmarks_zoo/registry.py unverified licence not identified · pointer only · d303d39673c61784 · report
load_model in 479 papers unibench/models_zoo/registry.py unverified licence not identified · pointer only · b81a08983be5a4ee · report

Tasks

Language ModelingLanguage ModellingObject RecognitionVisual Reasoning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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