Benchmark Hub

Featured Benchmarks

VibeCode Arena

VibeCode Arena

🏢
BenchFlow
code
Pokemon Gym

Pokemon Gym

🏢
BenchFlow
reasoning
JFK Arena

JFK Arena

🏢
BenchFlow
retrieval
PaperBench

PaperBench

🏢
OpenAI
agent
WebArena

WebArena

🏢
Carnegie Mellon University
agent
SWE-Bench

SWE-Bench

🏢
Princeton NLP
code
RareBench

RareBench

🏢
chenxz1111
knowledge
Bird-SQL

Bird-SQL

🏢
AlibabaResearch
code
MedQA-CS

MedQA-CS

🏢
Bio-NLP
knowledge
WebCanvas

WebCanvas

🏢
iMeanAI
agent
MMLU-Pro

MMLU-Pro

🏢
TIGER-AI-Lab
knowledge

All Benchmarks