Tag: agent benchmarking
Browse our exclusive articles!
Rethinking Audio-Language Models: Text vs Audio Reliance
Explore new insights on audio-language models showing text priors often overshadow true audio reliance in evaluation benchmarks.
AgentSearchBench: Benchmark for Real-World AI Agent Search
Discover AgentSearchBench, a large-scale benchmark improving AI agent search with execution-aware evaluation for real-world task matching.
HalluAudio: Benchmark for Hallucination Detection in LALMs
Discover HalluAudio, the first large-scale benchmark to detect hallucinations in large audio-language models across speech, music, and environmental sounds...
IndiaFinBench: Benchmarking LLMs on Indian Finance Texts
IndiaFinBench is the first benchmark to evaluate large language models on Indian financial regulatory texts with expert annotations and diverse tasks.
RoboWM-Bench: Benchmark for Robotic Manipulation Models
RoboWM-Bench offers a unified benchmark to evaluate video world models in robotic manipulation, focusing on physical plausibility and executable actions.