| MAmmoTH-VL-8B |
- GPT-4 score
- 62.3
|
MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale 2024-12-06 |
코드 1 |
| Qwen2-VL-7B |
- GPT-4 score
- 62.0
|
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution 2024-09-18 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 |
| InternVL2-40B |
- GPT-4 score
- 61.8
|
연결 없음 논문 날짜 미기재 |
연결 없음 |
| Qwen-VL-Plus |
- GPT-4 score
- 61.1±0.2
|
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond 2023-08-24 |
코드 1 · 코드 2 |
| Mini-Gemini-HD-BS |
- GPT-4 score
- 60.8
|
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models 2024-03-27 |
코드 1 · 코드 2 |
| InternVL2.5-2B |
- GPT-4 score
- 60.8
- Params
- 2B
|
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling 2024-12-06 |
코드 1 |
| MAmmoTH-VL-8B (SI) |
- GPT-4 score
- 60.6
|
MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale 2024-12-06 |
코드 1 |
| InternVL2.5-4B |
- GPT-4 score
- 60.6
- Params
- 4B
|
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling 2024-12-06 |
코드 1 |
| GPT-4V-Turbo-detail:low |
- GPT-4 score
- 60.2±0.3
|
GPT-4 Technical Report 2023-03-15 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 |
| Mini-Gemini-HD |
- GPT-4 score
- 59.3
|
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models 2024-03-27 |
코드 1 · 코드 2 |
| Claude 3 Opus (claude-3-opus-20240229) |
- GPT-4 score
- 58.1±0.1
|
연결 없음 논문 날짜 미기재 |
연결 없음 |
| GLM-4V-9B |
- GPT-4 score
- 58.0
|
CogVLM2: Visual Language Models for Image and Video Understanding 2024-08-29 |
코드 1 · 코드 2 · 코드 3 |
| LLaVA-OneVision-7B |
- GPT-4 score
- 57.5
|
LLaVA-OneVision: Easy Visual Task Transfer 2024-08-06 |
코드 1 · 코드 2 |
| LLaVA-NeXT-34B |
- GPT-4 score
- 57.4
- Params
- 34B
|
연결 없음 논문 날짜 미기재 |
연결 없음 |
| Meteor |
- GPT-4 score
- 57.3
- Params
- 7B
|
Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models 2024-05-24 |
코드 1 |
| CROME (Vicuna-13B) |
- GPT-4 score
- 55.1
|
CROME: Cross-Modal Adapters for Efficient Multimodal LLM 2024-08-13 |
연결 없음 |
| IXC2-4KHD |
- GPT-4 score
- 54.9
|
InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD 2024-04-09 |
코드 1 · 코드 2 |
| Weitu-VL-1.0 |
- GPT-4 score
- 54.7
- Params
- 15B
|
연결 없음 논문 날짜 미기재 |
연결 없음 |
| TroL-7B |
- GPT-4 score
- 54.7
- Params
- 7B
|
TroL: Traversal of Layers for Large Language and Vision Models 2024-06-18 |
코드 1 |
| Mini-Gemini |
- GPT-4 score
- 53.0
|
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models 2024-03-27 |
코드 1 · 코드 2 |
| CogVLM(Vicuna-7B) |
- GPT-4 score
- 52.8
- Params
- 17B
|
CogVLM: Visual Expert for Pretrained Language Models 2023-11-06 |
코드 1 · 코드 2 · 코드 3 · 코드 4 |
| CogAgent |
- GPT-4 score
- 52.8
- Params
- 18B
|
CogAgent: A Visual Language Model for GUI Agents 2023-12-14 |
코드 1 · 코드 2 · 코드 3 |
| Qwen2-VL-2B (finetuned on GAP-VQA train) |
- GPT-4 score
- 52.43
|
Gamified crowd-sourcing of high-quality data for visual fine-tuning 2024-10-05 |
연결 없음 |
| InternVL2-26B (SGP, token ratio 9%) |
- GPT-4 score
- 52.10
- Params
- 26B
|
A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs 2024-12-04 |
코드 1 |
| MM1.5-30B |
- GPT-4 score
- 52.0
|
MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning 2024-09-30 |
연결 없음 |
| MiniCPM-Llama3-V-2.5-8B (finetuned on GAP-VQA train) |
- GPT-4 score
- 51.789
|
Gamified crowd-sourcing of high-quality data for visual fine-tuning 2024-10-05 |
연결 없음 |
| IXC-2.5-7B |
- GPT-4 score
- 51.7
|
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output 2024-07-03 |
코드 1 |
| InternLM-XComposer2 |
- GPT-4 score
- 51.2
|
InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model 2024-01-29 |
코드 1 |
| Lyra-Mini |
- GPT-4 score
- 51.2
- Params
- 3B
|
Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition 2024-12-12 |
코드 1 |
| CuMo-7B |
- GPT-4 score
- 51.0
- Params
- 7B
|
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts 2024-05-09 |
코드 1 |