🏷️ ai benchmarks

phi-4 microsoft research small language models synthetic data ai benchmarks

Google DeepMind Gemini 2.5 Ultra scientific research AI large language models AI benchmarks

Claude 4 Anthropic mathematical reasoning AI benchmarks large language models

Google Gemini Chatbot Arena LMSYS AI benchmarks large language models

Stanford HAI AI benchmarks AI agents real-world AI evaluation autonomous AI

DeepSeek R2 GPT-5 open-source AI reasoning models AI benchmarks

Mistral AI Codestral 2.0 coding AI GPT-4o AI benchmarks

Gemini 2.5 Ultra Google DeepMind multimodal AI AI benchmarks frontier models

Gemini 2.5 Ultra Google DeepMind million-token context large language models AI benchmarks

NIST DeepSeek V4 Pro AI benchmarks CAISI evaluation independent testing

NIST DeepSeek V4 Pro AI benchmarks CAISI evaluation AI safety

AI race China AI DeepSeek US AI policy AI benchmarks