CogArena: Benchmarking Multimodal Agents on Interactive Behavioral Experiments

We introduce CogArena, a benchmark of ten experimental paradigms from the social and behavioral sciences. It comes from a paper posted to arXiv on 29 October 2026. Claims about the cognitive capabilities of large language models are typically tested by translating behavioral paradigms into text prompts, bypassing the visual interfaces and time pressure through which human participants actually engage with experiments. At the same time, AI agents can now complete online behavioral tasks and produce human-like data, which raises concerns that online datasets in the social and behavioral sciences are increasingly open to contamination. Agents complete the experiments through a standard web browser, working with the same visual stimuli and response interfaces that online participants use. A three-level scoring procedure evaluates whether the agent completed the task, how accurately it performed, and whether its data show the behavioral signatures each paradigm reliably produces in people. Across four multimodal models, each run ten times per task, we find that finishing an experiment and reproducing its signatures are different things. Many sessions did not finish, and those that did reproduced some signatures reliably and others not at all. CogArena provides the tasks, scoring code, and a public leaderboard for new submissions.

Why it counts

We introduce CogArena, a benchmark of ten experimental paradigms from the social and behavioral sciences.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.