SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.06591 · 2024

Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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; 3 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 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/2401.06591.json · badge: /api/ran/2401.06591.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
kaistai/prometheus-vision canonical (classifier label)
classifier basis not recorded on the link
7 ran · 0 no recorded run
FunctionStatusWhere it lives
expand2square Ran
ran; our contract draft was wrong, not the code
kaistai/prometheus-vision/llava/mm_utils.py
code served (permissive licence) · get_code("592b3c1a88f93d7c")
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) and returned Image. 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.

from PIL import Image

# Create a small test image (non-square)
pil_img = Image.new('RGB', (8, 6), color='red')

# Define background color for padding
background_color = (255, 255, 255)

ARGS = {
    'pil_img': pil_img,
    'background_color': background_color,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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_chunk Ran
ran; our contract draft was wrong, not the code
kaistai/prometheus-vision/llava/eval/model_vqa.py
code served (permissive licence) · get_code("42a46570620cd9fa")
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) and returned list, ndim 1, dtype family int; 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 math

def split_list(lst, n):
    """Split a list into n (roughly) equal-sized chunks"""
    chunk_size = math.ceil(len(lst) / n)
    return [lst[i:i + chunk_size] for i in range(0, len(lst), chunk_size)]

def get_chunk(lst, n, k):
    chunks = split_list(lst, n)
    return chunks[k]

# Setup code
lst = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
n = 3
k = 1

ARGS = {
    "lst": lst,
    "n": n,
    "k": k
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 int — 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
is_none Ran
ran, violated the contract we drafted
kaistai/prometheus-vision/llava/eval/model_vqa_mmbench.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ASTRAL-Group/ASTRA, is pointer only (licence: NONE) · get_code("bae18947b56f2be1")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ASTRAL-Group/ASTRA, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_image Ran
ran, honoured the contract we drafted
kaistai/prometheus-vision/llava/eval/model_vqa_qbench.py
code served (permissive licence) · get_code("9b3c1cb391672ccb")
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 Image. 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
from PIL import Image
import os

# Create a temporary image file for testing
temp_dir = tempfile.mkdtemp()
temp_image_path = os.path.join(temp_dir, "test_image.jpg")

# Create a simple test image
test_image = Image.new('RGB', (100, 100), color=(73, 109, 137))
test_image.save(temp_image_path)

# Define ARGS with a local file path
ARGS = {
    'image_file': temp_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, requests — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
load_image_from_base64 Ran
ran, honoured the contract we drafted
kaistai/prometheus-vision/llava/mm_utils.py
code served (permissive licence) · get_code("c3ee9d07c900dd55")
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 PngImageFile. 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 base64
from PIL import Image
from io import BytesIO
import numpy as np

# Create a small valid image in memory
img_array = np.uint8(np.random.rand(10, 10, 3) * 255)
img = Image.fromarray(img_array, mode='RGB')

# Encode to base64
buffer = BytesIO()
img.save(buffer, format='PNG')
buffer.seek(0)
image_base64 = base64.b64encode(buffer.read()).decode('utf-8')

ARGS = {
    'image': image_base64
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PngImageFile — a PngImageFile output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PngImageFile output the recorded ndim 3 and dtype family int 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
process_images Ran
ran, honoured the contract we drafted
kaistai/prometheus-vision/llava/mm_utils.py
code served (permissive licence) · get_code("344dff4791fd1381")
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 4, dtype family float, shape (2, 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.

from PIL import Image
import torch
import numpy as np

torch.manual_seed(0)

# Create a minimal image processor mock
class MockImageProcessor:
    def __init__(self):
        self.image_mean = [0.5, 0.5, 0.5]  # normalized values
    
    def preprocess(self, image, return_tensors=None):
        # Convert PIL image to tensor
        img_array = np.array(image).astype(np.float32) / 255.0
        # Convert to (C, H, W) format
        if len(img_array.shape) == 3:
            img_tensor = torch.from_numpy(img_array).permute(2, 0, 1)
        else:
            img_tensor = torch.from_numpy(img_array).unsqueeze(0)
        return {'pixel_values': img_tensor.unsqueeze(0)}
    
    def __call__(self, images, return_tensors=None):
        # Handle batch of images
        processed = []
        for img in images:
            img_array = np.array(img).astype(np.float32) / 255.0
            if len(img_array.shape) == 3:
                img_tensor = torch.from_numpy(img_array).permute(2, 0, 1)
            else:
                img_tensor = torch.from_numpy(img_array).unsqueeze(0)
            processed.append(img_tensor)
        stacked = torch.stack(processed, dim=0)
        return {'pixel_values': stacked}

# Create a minimal model config mock
class MockModelConfig:
    def __init__(self, image_aspect_ratio=None):
        self.image_aspect_ratio = image_aspect_ratio

# Create sample PIL images with different sizes
# First image: 4x3 (width x height)
img1 = Image.new('RGB', (4, 3), color=(100, 150, 200))
# Second image: 3x4 (width x height) - different aspect ratio
img2 = Image.new('RGB', (3, 4), color=(50, 100, 150))

images = [img1, img2]
image_processor = MockImageProcessor()
model_cfg = MockModelConfig(image_aspect_ratio='pad')

ARGS = {
    'images': images,
    'image_processor': image_processor,
    'model_cfg': model_cfg
}
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 4, dtype family float, shape (2, 3, 4, 4) — shape (2, 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
split_list Ran
ran; our contract draft was wrong, not the code
kaistai/prometheus-vision/llava/eval/model_vqa.py
code served (permissive licence) · get_code("076c252c52cbb161")
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) and returned list. 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 math

def split_list(lst, n):
    """Split a list into n (roughly) equal-sized chunks"""
    chunk_size = math.ceil(len(lst) / n)
    return [lst[i:i + chunk_size] for i in range(0, len(lst), chunk_size)]

# Setup code
lst = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
n = 3

ARGS = {
    "lst": lst,
    "n": n
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 — a list 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

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 7 the same month, 7 later) and 0 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
22 dated earlier, 3 the same month, 165 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
get_chunk 189 other papers
21 dated earlier, 3 the same month, 159 later, 6 same year, order not determinable
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 186 more not named here
load_image 85 other papers
12 dated earlier, 1 the same month, 68 later, 4 same year, order not determinable
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2305.10973 (2023-05)
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
2307.10490 (2023-07)
Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs
and 82 more not named here
load_image_from_base64 85 other papers
16 dated earlier, 5 the same month, 60 later, 4 same year, order not determinable
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2308.10253 (2023-08)
StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
2309.07120 (2023-09)
Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics
and 82 more not named here
is_none 83 other papers
9 dated earlier, 2 the same month, 70 later, 2 same year, order not determinable
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2308.10253 (2023-08)
StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
2308.13566 (2023-08)
MLLM-DataEngine: An Iterative Refinement Approach for MLLM
and 80 more not named here
expand2square 68 other papers
12 dated earlier, 4 the same month, 49 later, 3 same year, order not determinable · 1 only as an assembly brick
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2204.03541 (2022-04)
End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge Distillation
2308.10253 (2023-08)
StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
and 65 more not named here
process_images 44 other papers
9 dated earlier, 3 the same month, 29 later, 3 same year, order not determinable · 1 only as an assembly brick
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2308.10253 (2023-08)
StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
2310.01779 (2023-10)
HallE-Control: Controlling Object Hallucination in Large Multimodal Models
and 41 more not named here

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

Assessing long-form responses generated by Vision-Language Models (VLMs) is challenging. It not only requires checking whether the VLM follows the given instruction but also verifying whether the text output is properly grounded on the given image. Inspired by the recent approach of evaluating LMs with LMs, in this work, we propose to evaluate VLMs with VLMs. For this purpose, we present a new feedback dataset called the Perception Collection, encompassing 15K customized score rubrics that users might care about during assessment. Using the Perception Collection, we train Prometheus-Vision, the first open-source VLM evaluator model that can understand the user-defined score criteria during evaluation. Prometheus-Vision shows the highest Pearson correlation with human evaluators and GPT-4V among open-source models, showing its effectiveness for transparent and accessible evaluation of VLMs. We open-source our code, dataset, and model at https://github.com/kaistAI/prometheus-vision

For agents

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

get_harvested_code_for_paper("2401.06591")
get_code_for_paper("2401.06591")
have("2401.06591")

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

curl https://syntology.ai/api/ran/2401.06591.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.06591.svg)](https://syntology.ai/paper/2401.06591)

Connect an agent — have() is free.