/ Benchmarks

Open ASR Leaderboard adds Egyptian and Nigerian accents for better global testing

2 days ago

OpenAI introduced LifeVal: a benchmark for assessing the practical utility of AI

5 days ago

LlamaIndex unveils BooBench to stress-test document parsers

1 week ago

New Benchmark Tests AI Agents on Complex Software Building

1 week ago

BenchMIRT Reveals What LLM Tests Really Measure

2 months ago

API settings nearly tripled GPT-5.6 Sol's score

3 months ago

VoiceEQ Tests Whether Voice AI Actually Sounds Human

3 months ago

Perplexity Open-Sources WANDR Benchmark for AI Research Agents

3 months ago

OpenAI audit finds major flaws in SWE-Bench Pro

3 months ago

OpenAI introduced GeneBench-Pro for AI testing in biology

4 months ago