InfiBench

InfiBench (Data Part) Note: For full description, please visit our main website https://infi-coder.github.io/infibench. This repo contains all data of our code LLM evaluation dataset InfiBench. suite_v2.1.yaml lists the case list and suite_v2.1_data.csv records all data (prompt, reference answer, evaluation metric). Th

Papers using InfiBench (4)

VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models2025CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance2025VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models2025InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models2024