多项力压 Grok 4、OpenAI o3，谷歌推出 Gemini 2.5 Deep Think 模型
"基准测试" 相关文章
The Ultimate 2025 Guide to Coding LLM Benchmarks and Performance Metrics
UserBench: An Interactive Gym Environment for User-Centric Agents
CompoST: A Benchmark for Analyzing the Ability of LLMs To Compositionally Interpret Questions in a QALD Setting
About 30% of Humanity’s Last Exam chemistry/biology answers are likely wrong
Benchmarking and Analyzing Generative Data for Visual Recognition
Protein-SE(3): Benchmarking SE(3)-based Generative Models for Protein Structure Design
CrossPL: Evaluating Large Language Models on Cross Programming Language Code Generation
Can LLMs Solve ASP Problems? Insights from a Benchmarking Study (Extended Version)
OS-MAP: How Far Can Computer-Using Agents Go in Breadth and Depth?
GAIA基准测试介绍
AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Data
TELEVAL: A Dynamic Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarios
Reasoning Beyond the Obvious: Evaluating Divergent and Convergent Thinking in LLMs for Financial Scenarios
Benchmarks for AI in Software Engineering
CausalStep: A Benchmark for Explicit Stepwise Causal Reasoning in Videos
confopt: A Library for Implementation and Evaluation of Gradient-based One-Shot NAS Methods
SDBench: A Comprehensive Benchmark Suite for Speaker Diarization
Document Haystack: A Long Context Multimodal Image/Document Understanding Vision LLM Benchmark
ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation
