SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.05343 · 2024

M3GIA: A Cognition Inspired Multilingual and Multimodal General Intelligence Ability Benchmark

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 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; 5 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2406.05343.json · badge: /api/ran/2406.05343.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
songweii/M3GIA canonical (classifier label)
classifier basis: census
5 ran · 3 no recorded run
FunctionStatusWhere it lives
chat_completion_openai Ran
ran; our contract draft was wrong, not the code
songweii/M3GIA/utils/eval_utils.py
code served (permissive licence) · get_code("17578ed4abc1e34f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. 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 openai
import time

# Mock the openai module since we can't make real API calls
class MockChatCompletion:
    @staticmethod
    def create(model, messages, n, temperature, max_tokens):
        return {
            'choices': [
                {
                    'message': {
                        'content': 'This is a mock response from the assistant.'
                    }
                }
            ]
        }

openai.ChatCompletion = MockChatCompletion
openai.error = type('error', (), {'OpenAIError': Exception})()

ARGS = {
    'model': 'gpt-3.5-turbo',
    'prompt': 'What is the capital of France?',
    'temperature': 0.7,
    'max_tokens': 100,
    'api_dict': {
        'api_base': 'https://api.openai.com/v1',
        'api_key': 'sk-test-key-12345'
    }
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
openai — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_multi_choice_info Ran
ran; our contract draft was wrong, not the code
songweii/M3GIA/utils/data_utils.py
code served (permissive licence) · get_code("811b35dbfb4c4959")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. 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 torch

# The function get_multi_choice_info takes a list of options and processes them
# It doesn't use torch or any complex objects, just strings/basic Python types

# Create a simple list of options for a multiple choice question
options = ["Paris", "London", "Berlin", "Madrid"]

# Construct the ARGS dictionary
ARGS = {
    "options": options
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
llava_image_processor Ran
ran; our contract draft was wrong, not the code
songweii/M3GIA/utils/model_utils.py
code served (permissive licence) · get_code("e4e30d1813045cfb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (3, 4, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 torch
import torch.nn as nn
from PIL import Image
import numpy as np

torch.manual_seed(0)

# Create a minimal stand-in for vis_processors
class MockVisProcessor(nn.Module):
    def __init__(self):
        super().__init__()
    
    def preprocess(self, raw_image, return_tensors=None):
        # Create a small tensor output
        # The function expects: vis_processors.preprocess(...)['pixel_values'][0]
        # So we need to return a dict with 'pixel_values' key containing a tensor
        pixel_values = torch.randn(1, 3, 4, 4)  # batch=1, channels=3, height=4, width=4
        return {'pixel_values': pixel_values}

# Create a small PIL Image as raw_image
raw_image = Image.new('RGB', (8, 8), color='red')

# Create the vis_processors mock
vis_processors = MockVisProcessor()

ARGS = {
    'raw_image': raw_image,
    'vis_processors': vis_processors
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (3, 4, 4) — shape (3, 4, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
load_yaml Ran
ran; our contract draft was wrong, not the code
songweii/M3GIA/utils/data_utils.py
code served (permissive licence) · get_code("ce93b7e192e1a8b7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) 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 tempfile
import os
import yaml

# Create a temporary YAML file with valid content
temp_dir = tempfile.mkdtemp()
yaml_file_path = os.path.join(temp_dir, "test.yaml")

# Write a simple valid YAML file
yaml_content = {
    "name": "test_config",
    "value": 42,
    "nested": {
        "key": "value",
        "list": [1, 2, 3]
    }
}

with open(yaml_file_path, 'w') as f:
    yaml.dump(yaml_content, f)

ARGS = {
    "file_path": yaml_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — 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
parse_img_path Ran
ran; our contract draft was wrong, not the code
songweii/M3GIA/utils/data_utils.py
code served (permissive licence) · get_code("de4427887bed9253")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 re

def parse_img_path(text):
    matches = re.findall("<img='(.*?)'>", text)
    return matches

ARGS = {
    "text": "This is a test <img='path/to/image1.png'> and another <img='path/to/image2.jpg'> in the text."
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
call_llava_engine_df Not yet run
unverified (harvested, no recorded run)
songweii/M3GIA/utils/model_utils.py
code served (permissive licence) · get_code("13d85e019721605f")
How it ran

no invocation recorded.

chat_completion_openai_azure Not yet run
unverified (harvested, no recorded run)
songweii/M3GIA/utils/eval_utils.py
code served (permissive licence) · get_code("ce06f1beecb5353c")
How it ran

no invocation recorded.

split_list Not yet run
unverified (harvested, no recorded run)
songweii/M3GIA/utils/eval_utils.py
code served (permissive licence) · get_code("edc961aa91ed2f95")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 5 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 5 later) and 3 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.

FunctionAlso present inEarliest-datedOthers named
split_list 197 other papers
60 dated earlier, 22 the same month, 108 later, 6 same year, order not determinable, 1 undated
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2306.17107 (2023-06)
LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding
2307.10490 (2023-07)
Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs
and 194 more not named here
load_yaml 6 other papers
1 dated earlier, 2 the same month, 3 later
2402.11530 (2024-02)
Efficient Multimodal Learning from Data-centric Perspective
2406.13642 (2024-06)
SpatialBot: Precise Spatial Understanding with Vision Language Models
2406.14852 (2024-06)
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
and 3 more not named here
parse_img_path 5 other papers
1 dated earlier, 4 later
2402.14418 (2024-02)
Uncertainty-Aware Evaluation for Vision-Language Models
Yang_PVC_Progressive_Visual_Token_Compression_for_Unified_Image_and_Video_CVPR_2025_paper (2025 (year only))
PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models
2502.00698 (2025-02)
MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Models
and 2 more not named here
get_multi_choice_info 2 other papers
2 later
Yang_PVC_Progressive_Visual_Token_Compression_for_Unified_Image_and_Video_CVPR_2025_paper (2025 (year only))
PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models
2509.19003 (2025-09)
Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards
llava_image_processor 1 other paper
1 later
2502.00698 (2025-02)
MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Models

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

As recent multi-modality large language models (MLLMs) have shown formidable proficiency on various complex tasks, there has been increasing attention on debating whether these models could eventually mirror human intelligence. However, existing benchmarks mainly focus on evaluating solely on task performance, such as the accuracy of identifying the attribute of an object. Combining well-developed cognitive science to understand the intelligence of MLLMs beyond superficial achievements remains largely unexplored. To this end, we introduce the first cognitive-driven multi-lingual and multi-modal benchmark to evaluate the general intelligence ability of MLLMs, dubbed M3GIA. Specifically, we identify five key cognitive factors based on the well-recognized Cattell-Horn-Carrol (CHC) model of intelligence and propose a novel evaluation metric. In addition, since most MLLMs are trained to perform in different languages, a natural question arises: is language a key factor influencing the cognitive ability of MLLMs? As such, we go beyond English to encompass other languages based on their popularity, including Chinese, French, Spanish, Portuguese and Korean, to construct our M3GIA. We make sure all the data relevant to the cultural backgrounds are collected from their native context to avoid English-centric bias. We collected a significant corpus of data from human participants, revealing that the most advanced MLLM reaches the lower boundary of human intelligence in English. Yet, there remains a pronounced disparity in the other five languages assessed. We also reveals an interesting winner takes all phenomenon that are aligned with the discovery in cognitive studies. Our benchmark will be open-sourced, with the aspiration of facilitating the enhancement of cognitive capabilities in MLLMs.

For agents

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

get_harvested_code_for_paper("2406.05343")
get_code_for_paper("2406.05343")
have("2406.05343")

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

curl https://syntology.ai/api/ran/2406.05343.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.05343.svg)](https://syntology.ai/paper/2406.05343)

Connect an agent — have() is free.