Blog

Multimodal SFT data for the win: Pushing model performance in the real world

Toloka Platform Relaunch

Toloka's advanced benchmarking reveals limitations and opportunities for LLMs

New Multimodal Benchmark Reveals Best LLMs for University-Level Math Challenges

U-MATH & μ-MATH: New university-level math benchmarks challenge LLMs

Can LLMs eliminate toxicity in human and AI-generated content? What multilingual research shows

Multimodal AI: Collaborative Emotion Labeling in Audio Data

Are LLMs good at natural sciences? A complex benchmark across 10 subject areas

Multi-domain, multi-language SFT dataset pushes LLM performance to the next level