AgentBench

Tests LLMs as interactive agents across eight environments (OS, database, knowledge graph, card game, puzzles, household, web shopping, web browsing); most modern harnesses implement only its OS slice.

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categoryagentic
Subcategorymulti-environment interactive LLM-as-agent evaluation (8 environments)
Page statusactive
Metricenvironment-specific metric (Success Rate, F1, Reward, or Game Progress), combined into an overall weighted score across all eight environments
Directionhigher_is_better
Dataset size1360
Dataset licenceApache-2.0
PublisherTsinghua University, with The Ohio State University

What it measures

AgentBench puts a model in the loop of a multi-turn interaction with a real or simulated environment and asks it to complete a task by issuing actions -- shell commands, SQL queries, dialogue moves, game actions -- rather than answering a single question. It spans eight distinct environments, five built specifically for the benchmark (Operating System, Database, Knowledge Graph, a Digital Card Game, and Lateral Thinking Puzzles) and three adapted from existing published environments (ALFWorld for household tasks, WebShop for web shopping, and Mind2Web for web browsing). Each environment exercises a different mix of instruction-following, long-horizon planning and environment-grounded decision-making.

Task format

Multi-turn interaction loop, up to 5-35 estimated turns depending on environment; the model issues an action each turn (bash/SQL command, dialogue act, game move) and receives an environment observation in response, until it completes the task, fails, or hits a turn limit.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub