AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?

Active

Tests whether AI agents can perform real-world time-consuming tasks on the web.

Publisher: Tel Aviv University
Domain: Assistants
License: mit
Published: Oct 2024
Notable for: Benchmark for evaluating Assistants.
Canonical: github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/assistant_bench

Cite

Notes

Only stored in your browser.

Attribution

README: github.com/UKGovernmentBEIS/inspect_evals/blob/main/src/inspect_evals/assistant_bench/eval.yamlMIT

Attribution policy →

FAQ

What is AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks??: Tests whether AI agents can perform real-world time-consuming tasks on the web.
What license is AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks? under?: AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks? is available under mit.