Trendoday

CogBattery: Human-Referenced Evaluation of Cognitive Task Behavior and Structure in Language Models

Human cognitive tasks let us compare language models with humans under controlled conditions. Yet a model can reproduce the direction of a human effect while making different errors. CogBattery evalua

  • Upvotes4
–Rank now
#26Peak rank
2Days on list
35Score · 7d
Nov 13, 2026First seen
Rank · 7 days

About this paper

CogBattery compares open-weight language models to humans across cognitive tasks, revealing that matching effect directions does not imply human-like error patterns or confidence calibration.

Human cognitive tasks let us compare language models with humans under controlled conditions. Yet a model can reproduce the direction of a human effect while making different errors. CogBattery evaluates 54 open-weight language models on text adaptations of 13 cognitive paradigms, comparing each with human data from its source study. Like humans, models respond more to n-back lures than to controls, yet they make far more false alarms on ordinary non-targets. Most models' reported confidence separates correct from incorrect answers less well than humans' does, and most always choose the same wager, including models that classify accurately. These patterns span many model families. Across…

language modelsn-back luresfalse alarmsconfidence calibrationcognitive paradigmsCogBatterymodel scalecognitive groupings
Upvotes
4
Authors
4
Published
Oct 30, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

CogBattery: Human-Referenced Evaluation of Cognitive Task Behavior and Structure in Language Models was first seen on Hugging Face · Daily papers on Nov 13, 2026. Since then it has appeared in 10 checks on 2 different days. Its best position was #26 of 30, reached on Nov 13, 23:28 UTC. It dropped off the list after Nov 14, 01:28 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 01:2807:2813:2819:2801:28 Nov 13, 01:28 UTC · #30Nov 13, 09:28 UTC · #30Nov 13, 11:28 UTC · #28Nov 13, 13:28 UTC · #28Nov 13, 15:28 UTC · #28Nov 13, 17:28 UTC · #28Nov 13, 19:28 UTC · #28Nov 13, 21:28 UTC · #27Nov 13, 23:28 UTC · #26Nov 14, 01:28 UTC · #27

Last 14 days

Best rank per day (UTC).

Nov 3today

Metric history

Platform metric as reported by Hugging Face.

0134 01:2807:2813:2819:2801:28 Nov 13, 01:28 UTC · 4Nov 13, 09:28 UTC · 4Nov 13, 11:28 UTC · 4Nov 13, 13:28 UTC · 4Nov 13, 15:28 UTC · 4Nov 13, 17:28 UTC · 4Nov 13, 19:28 UTC · 4Nov 13, 21:28 UTC · 4Nov 13, 23:28 UTC · 4Nov 14, 01:28 UTC · 4

Questions

Is CogBattery: Human-Referenced Evaluation of Cognitive Task Behavior and Structure in Language Models trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 14, 01:28 UTC, after 2 days of trending.

What is the highest rank CogBattery: Human-Referenced Evaluation of Cognitive Task Behavior and Structure in Language Models reached?

#26 on Hugging Face · Daily papers, on Nov 13, 23:28 UTC. Trendoday checks this list every 120 minutes.

How long has CogBattery: Human-Referenced Evaluation of Cognitive Task Behavior and Structure in Language Models been trending?

It was first seen on Nov 13, 2026 and has been on the list on 2 days (10 checks) since.