Glossary / Benchmark

Benchmark

A standard test used to compare AI models, such as a set of coding tasks or exam questions. A high score does not always mean better real-world performance.

Also written as: benchmarks

In the news

• Google Releases Android Bench 2.0 With Long-Horizon Tasks and Agentic Evaluation4h ago
• AI Leaderboard Platform Arena Raises $200 Million at $3.1 Billion Valuation1d ago
• Anthropic Releases Claude Haiku 5.5 With Lower Prices And Major Performance Jumps2d ago
• Sigil Wen Launches Underdog, a Private AI Assistant Competitor3d ago
• Google Releases EmbeddingGemma 2 Multimodal Vector Model3d ago
• Google Releases Nano Banana 2.1 Image Model With Lower Prices3d ago
• Gamma Launches Version 5 To Reduce AI Presentation Sameness3d ago
• Researchers Expand LeCun JEPA AI Into Universal World Model3d ago
• Deepseek Eyes $15 Billion Funding Round And 2027 IPO3d ago
• Mistral Releases One-Trillion-Parameter Mistral Large 43d ago
• Reflection debuts Beam, an open-weight AI model to rival Chinese competitors4d ago
• Reka AI Releases Rho-1 Omni-Model for Text, Images, Video, and Robotics4d ago