← All notes

Short answer

AgentBench tests LLMs as agents across 8 interactive environments. OSWorld tests multimodal agents on open-ended tasks on real computers. AgentBench found that poor long-term reasoning, decision-making and instruction following are the main reasons agents fail. [S1][S2]

Claims

• id: C1 claim: AgentBench consists of 8 distinct environments. source: S1 evidence: "a multi-dimensional benchmark that consists of 8 distinct environments"
• id: C2 claim: Poor long-term reasoning and instruction following are main obstacles. source: S1 evidence: "poor long-term reasoning, decision-making, and instruction following abilities are the main obstacles"
• id: C3 claim: Existing benchmarks often lack an interactive environment. source: S2 evidence: "existing benchmarks either lack an interactive environment"

Sources

• [S1] [2308.03688] AgentBench: Evaluating LLMs as Agents. arXiv. https://arxiv.org/abs/2308.03688 . License: CC BY 4.0. Accessed 2026-11-04.
• [S2] [2404.07972] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments. arXiv. https://arxiv.org/abs/2404.07972 . License: CC BY 4.0. Accessed 2026-11-04.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Summary by iinventedlight (AI-assisted).

@misc{iil_note_jbtgjwrq,
  author = {{iinventedlight}},
  title = {{Agent benchmarks: AgentBench and OSWorld}},
  howpublished = {iinventedlight Library},
  year = {2026},
  date = {2026-11-04},
  url = {https://iinventedlight.com/library/notes/ao-evals-agentbench-osworld/},
  note = {Permanent ID iil:note:jbtgjwrq. License: CC-BY-4.0.},
}

Markdown

Spotted a mistake? Use the MCP feedback tool or email hello@iinventedlight.com.

For language models and agents: start at /llms.txt. This page in Markdown: /library/notes/ao-evals-agentbench-osworld.md.