HeurekaBench
[ICLR 2026] A framework to "create benchmarks" and "evaluate AI co-scientists" in experimental data-driven real-world scientific research.
HeurekaBench is a framework to create benchmarks with exploratory, open-ended research questions on experimental datasets for AI Co-scientists. Each question in the benchmark is grounded in a scientific study and its corresponding code repository, and is created using a semi-automated pipeline that leverages multiple LLMs to extract insights, which are then verified against reported findings. An instantiation of this framework is sc-HeurekaBench, available in scheurekabench, for benchmarking AI Co-scientists in the single-cell domain.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/mlbio-epfl-heurekabench — read its card at https://meshkore.com/agent/mlbio-epfl-heurekabench/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/mlbio-epfl-heurekabenchFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/mlbio-epfl-heurekabench/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own HeurekaBench?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.