Multimodal STEM problem set for verifiable, answer-supervised training and RL: contains single-image, multi-panel, and multi-image PhD-level questions across physics, math, chemistry and biology. Each example has a deterministic ground-truth answer, enabling reward modeling and automated evaluation.
[next-mdx-remote-client] error compiling MDX: Unexpected character `1` (U+0031) before name, expected a character that can start a name, such as a letter, `$`, or `_` More information: https://mdxjs.com/docs/troubleshooting-mdx
Evaluates retrievers and search agents on synthetic multi-hop questions that require assembling a complete set of supporting evidence. Provides English and Russian variants (395 questions each), a fixed dense index embedded with Qwen3-Embedding-8B, and BrowseComp-Plus evaluation integrations.
Provides re-annotated academic video instruction data for captioning, video QA, and fine-grained motion understanding; rewrites short answers and concise captions into evidence-grounded, instruction-following responses and supplies JSONL annotation files (original videos not included).
Provides 324 Russian short-answer web-search tasks with gold supporting documents to evaluate fixed-index retrievers and search agents. Tasks span eight topical categories and five retrieval challenge types (multihop, structured evidence, temporal, entity disambiguation, comparative) and use a Qwen3-Embedding-8B index for evaluation.
