SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.09889 · ACL Findings · 2021

GEM: A General Evaluation Benchmark for Multimodal Tasks

Nan Duan, Ming Zhong, Lei Ji, Yongfei Liu, Huaishao Luo, Lin Su, Edward Cui, Chenfei Wu, Taroon Bharti, Arun Sacheti

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; 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/2106.09889.json · badge: /api/ran/2106.09889.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
microsoft/GEM canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_metrics Ran
ran; our contract draft was wrong, not the code
microsoft/GEM/evaluation/metric-retrieval.py
code served (permissive licence) · get_code("593322fdfd62e04e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned dict. 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 numpy as np

# The function expects x to be a 2D numpy array where:
# - It computes sort(-x, axis=1) to sort each row in descending order of x
# - It extracts diagonal elements d = np.diag(-x), which requires x to be square
# - It finds where sorted values equal diagonal values to get rankings
# - The diagonal represents "correct" matches (like similarity scores where diagonal is the true pair)

# Create a small square matrix (5x5) representing similarity scores
# Diagonal should have high values (correct matches), off-diagonal lower values
np.random.seed(42)
n = 5
x = np.random.rand(n, n) * 0.5  # Random values between 0 and 0.5

# Make diagonal values higher (correct matches should rank well)
for i in range(n):
    x[i, i] = 0.7 + np.random.rand() * 0.3  # Diagonal values between 0.7 and 1.0

ARGS = {'x': x}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.

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

In this paper, we present GEM 1 as a General Evaluation benchmark for Multimodal tasks. Different from existing datasets such as GLUE (Wang et al., 2018), SuperGLUE (Wang et al., 2019), XGLUE (Liang et al., 2020) and XTREME (Hu et al., 2020) that mainly focus on natural language tasks, GEM is a largescale vision-language benchmark, which consists of GEM-I for image-language tasks and GEM-V for video-language tasks. Comparing with existing multimodal datasets such as MSCOCO (Chen et al., 2015) and Flicker30K (Vinyals et al., 2015) for image-language tasks, YouCook2 (Zhou et al., 2018) and MSR-VTT (Xu et al., 2016) for video-language tasks, GEM is not only the largest vision-language dataset covering image-language tasks and video-language tasks at the same time, but also labeled in multiple languages. We also provide two baseline models for this benchmark. We will release the dataset, code and baseline models, aiming to advance the development of multilingual multimodal research.

For agents

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

get_harvested_code_for_paper("2106.09889")
get_code_for_paper("2106.09889")
have("2106.09889")

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

curl https://syntology.ai/api/ran/2106.09889.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.09889.svg)](https://syntology.ai/paper/2106.09889)

Connect an agent — have() is free.