/ Benchmarks

API settings nearly tripled GPT-5.6 Sol's score

1 week ago

VoiceEQ Tests Whether Voice AI Actually Sounds Human

3 weeks ago

Perplexity Open-Sources WANDR Benchmark for AI Research Agents

3 weeks ago

OpenAI audit finds major flaws in SWE-Bench Pro

1 month ago

OpenAI introduced GeneBench-Pro for AI testing in biology

1 month ago