{"paper":{"title":"CheeseBench: Evaluating Large Language Models on Rodent Behavioral Neuroscience Paradigms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Open-weight LLMs reach only 53 percent success on ASCII versions of classic rodent tasks where animals average 79 percent.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Zacharie Bugaud","submitted_at":"2026-04-12T21:37:26Z","abstract_excerpt":"We introduce CheeseBench, a benchmark that evaluates large language models (LLMs) on nine classical behavioral neuroscience paradigms (Morris water maze, Barnes maze, T-maze, radial arm maze, star maze, operant chamber, shuttle box, conditioned place preference, and delayed non-match to sample), spanning six cognitive dimensions. Each task is grounded in peer-reviewed rodent protocols with approximate animal baselines. The agent receives a unified system prompt with no task-specific instructions and must discover goals purely from ASCII text observations and reward signals, much like a rodent "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Under this unified zero-shot ASCII protocol, current open-weight LLM agents remain well below approximate rodent reference values, particularly on tasks requiring spatial navigation and within-trial state tracking.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The ASCII text renderings of the tasks accurately capture the core cognitive and perceptual demands of the original rodent behavioral paradigms without introducing artifacts that alter difficulty.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LLMs reach 52.6% average success on text-based rodent neuroscience tasks, above random agents at 32.1% but below approximate rodent baselines at 78.9%.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Open-weight LLMs reach only 53 percent success on ASCII versions of classic rodent tasks where animals average 79 percent.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cf72cf3f28c4c7f6aebf5c99fa4759044dabc47f5a1727f61d4425940cedc3d7"},"source":{"id":"2604.10825","kind":"arxiv","version":2},"verdict":{"id":"cca5bbe6-e395-4aa8-ad0e-a20bbc9712bd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:17:28.384818Z","strongest_claim":"Under this unified zero-shot ASCII protocol, current open-weight LLM agents remain well below approximate rodent reference values, particularly on tasks requiring spatial navigation and within-trial state tracking.","one_line_summary":"LLMs reach 52.6% average success on text-based rodent neuroscience tasks, above random agents at 32.1% but below approximate rodent baselines at 78.9%.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The ASCII text renderings of the tasks accurately capture the core cognitive and perceptual demands of the original rodent behavioral paradigms without introducing artifacts that alter difficulty.","pith_extraction_headline":"Open-weight LLMs reach only 53 percent success on ASCII versions of classic rodent tasks where animals average 79 percent."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.10825/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}