Skywork/Skywork-VL-Reward-7B

Introduction

The lack of multimodal reward models on the market has become a major bottleneck restricting the development of multimodal reinforcement technology. We open source the 7B multimodal reward model Skywork-VL-Reward, injecting new momentum into the industry and opening a new chapter in multimodal reinforcement learning

Skywork-VL-Reward is based on the Qwen2.5-VL-7B-Instruct architecture with the addition of a value head structure for training reward model. We obtained SOTA of 73.1 in VL-RewardBench and high score of 90.1 in RewardBench. In addition, our MPO trained on Skywork-R1V-2.0 further validates the effectiveness of the model. We hope that this multimodal reward model will contribute to the open source community! Please refer to our technical report for more details.

Technical Report

Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning

Evaluation

VL-RewardBench

Model Name	Model Size	General	Hallucination	Reasoning	Overall Accuracy	Macro Average
Proprietary Models
Claude-3.5-Sonnet(2024-06-22)	-	43.4	55.0	62.3	55.3	53.6
Gemini-1.5-Flash (2024-09-24)	-	47.8	59.6	58.4	57.6	55.3
GPT-4o(2024-08-06)	-	49.1	67.6	70.5	65.8	62.4
Gemini-1.5-Pro(2024-09-24)	-	50.8	72.5	64.2	67.2	62.5
Gemini-2.0-flash-exp(2024-12)	-	50.8	72.6	70.1	68.8	64.5
Open-Source Models
Qwen2-VL-7B-Instruct	7B	31.6	19.1	51.1	28.3	33.9
MAmmoTH-VL-8B	8B	36.0	40.0	52.0	42.2	42.7
Qwen2.5-VL-7B-Instruct	7B	43.4	42.0	63.0	48.0	49.5
InternVL3-8B	8B	60.6	44.0	62.3	57.0	55.6
IXC-2.5-Reward-7B	7B	80.3	65.3	60.4	66.3	68.6
Qwen2-VL-72B-Instruct	72B	38.1	32.8	58.0	39.5	43.0
Molmo-72B-0924	72B	33.9	42.3	54.9	44.1	43.7
QVQ-72B-Preview	72B	41.8	46.2	51.2	46.4	46.4
Qwen2.5-VL-72B-Instruct	72B	47.8	46.8	63.5	51.6	52.7
InternVL3-78B	78B	67.8	52.5	64.5	63.3	61.6
Skywork-VL Reward(Ours)	7B	66.0	80.0	61.0	73.1	69.0

---

RewardBench

Model Name	Chat	Chat Hard	Safety	Reasoning	Score
Language-Only Reward Models
InternLM2-7B-Reward	99.2	69.5	87.2	94.5	87.6
Skywork-Reward-Llama3.1-8B	95.8	87.3	90.8	96.2	92.5
Skywork-Reward-Llama-3.1-8B-v0.2	94.7	88.4	92.7	96.7	93.1
QRM-Llama3.1-8B-v2	96.4	86.8	92.6	96.8	93.1
Multi-Modal Reward Models
Qwen2-VL-7B-Instruct	65.1	50.9	55.8	68.3	60.0
InternVL3-8B	97.2	50.4	83.6	83.9	78.8
Qwen2.5-VL-7B-Instruct	94.3	63.8	84.1	86.2	82.1
IXC-2.5-Reward-7B	90.8	83.8	87.8	90.0	88.1
Skywork-VL Reward(Ours)	90.0	87.5	91.1	91.8	90.1

---

Usage

Set Up the Environment

conda create -n vl-reward python=3.11
conda activate vl-reward
bash setup.sh

Run the Inference Code

import torch
from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration
from trl import AutoModelForCausalLMWithValueHead
from qwen_vl_utils import process_vision_info
from transformers.utils import cached_file
from safetensors import safe_open


processor = AutoProcessor.from_pretrained("Skywork/Skywork-VL-Reward-7B")
# The default range for the number of visual tokens per image in the model is 4-16384.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# min_pixels = 256*28*28
# max_pixels = 1280*28*28
# processor = AutoProcessor.from_pretrained("Skywork/Skywork-VL-Reward-7B", min_pixels=min_pixels, max_pixels=max_pixels)

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "Skywork/Skywork-VL-Reward-7B",
    device_map="auto",
    torch_dtype=torch.bfloat16,
)
# We recommend enabling flash_attention_2 for better acceleration and memory saving
# pip install flash-attn --no-build-isolation
#
# model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
#     "Skywork/Skywork-VL-Reward-7B",
#     device_map="auto",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
# )

model = AutoModelForCausalLMWithValueHead.from_pretrained(model)
vhead_file = cached_file(
    path_or_repo_id="Skywork/Skywork-VL-Reward-7B", filename="value_head.safetensors"
)
with safe_open(vhead_file, framework="pt", device="cpu") as f:
    vhead_params = {key: f.get_tensor(key) for key in f.keys()}
model.load_state_dict(vhead_params, strict=False)
model.requires_grad_(False)
model.eval()

# score: 23.89
# if you use flash_attention_2 the score will be 23.76
demo_image = "demo.jpg"
demo_question = "Hint: Please answer the question and provide the correct option letter, e.g., A, B, C, D, at the end.\nQuestion: Is Purple the highest value?\nChoices:\n(A) no\n(B) yes"
demo_answer = "The answer is: B"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": demo_image,
            },
            {
                "type": "text",
                "text": demo_question,
            },
        ],
    },
    {
        "role": "assistant",
        "content": demo_answer,
    },
]
text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=False
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")
values = model(**inputs, return_dict=True, use_cache=False)[-1]
scores = values.gather(
    dim=-1, index=(inputs["attention_mask"].sum(dim=-1, keepdim=True) - 1)
)
score = scores[0].item()
print("Reward Score is: ", score)

Citation

If you use this work in your research, please cite:

@article{2025skyworkvlrm,
      title={Skywork-VL Reward: An Effective  Reward Model for Multimodal Understanding and Reasoning}, 
      author={Xiaokun Wang and Chris and Jiangbo Pei and Yunzhuo Hao and Weijie Qiu and Ai Jian and Tianyidan Xie and Xuchen Song and Yang Liu and Yahui Zhou},
      year={2025},
      url={https://github.com/SkyworkAI/Skywork-R1V/blob/main/SkyworkVL_RM.pdf}, 
}