PerceptionBench
PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models
LLM OrchestrationOpen Source AI & Machine LearningOpen Source
About
PerceptionBench is a benchmark designed to assess the atomic visual perception abilities of multimodal large language models (MLLMs). It addresses limitations in existing benchmarks by isolating perceptual errors from reasoning or domain knowledge failures. The benchmark includes 3,000 verified questions that target ten atomic perceptual capabilities, providing a structured approach to evaluate and diagnose the visual perception boundaries of MLLMs.
Open Source Health
- Stars
- 206
- Forks
- 11
- License
- Apache-2.0
- Last commit
- 2 months ago
Python
Alternatives to PerceptionBench
The Algorithmby TwitterSource code for the X Recommendation Algorithm
Recommendersby TensorFlowTensorFlow Recommenders is a library for building recommender system models using TensorFlow.- RPG_KDD2025by FacebookresearchThis repository provides the code for implementing RPG described in our KDD'25 paper "Generating Long Semantic IDs in Parallel for Recommendation".
- Pairecby AlibabaA Go web framework for quickly building recommendation online services based on JSON configuration.
Textrankby Summa NLPTextRank implementation for Python 3.
Resources & Links
Related Categories
Using PerceptionBench?
Track its cost next to the rest of your stack and get a reminder before it renews.
Add to my stackVendor
Moonshot AI
Open-source projects on GitHub: Kimi-Dev, MoonEP and Checkpoint Engine
