GAIA

GAIA

Source

GAIA community submissions (reviewed publisher results)

Version

2023-test

Measurement date

Not reported

Metric

% · Higher is better

Evaluation scope

Submitted system 'xManus v0.2'. Community-submitted answers; model identity is submitter-declared and execution is not independently verified. GAIA 2023 test split, 301 questions; operator-reported normalized quasi-exact-match accuracy. Declared model family 'claude-sonnet-4'. Submission date 2025-06-11; measurement date unreported. Submitter organization unreported. Pinned dataset revision 8be3178cbf290fdd9956f40514c7fa1ef4f780e0, zero-based source row 275. Tools, exact backend revision when undated, runtime agent commit, sampling settings, execution budget and repeats unreported. Current pinned scorer documents the method, not the code revision used for every historical submission. Submission-specific cohort; no cross-model ranking or independent reproduction. Contamination and manual intervention are not ruled out. Declared xManus version retained in system name; linked repository does not corroborate execution. Original submitted system prompt: Please answer the question below. You should: - Return only your answer, which should be a number, or a short phrase with as few words as possible, or a comma separated list of numbers and/or strings. - If the answer is a number, return only the number without any units unless specified otherwise. - If the answer is a string, don't include articles, and don't use abbreviations (e.g. for states). - If the answer is a comma separated list, apply the above rules to each element in the list.

Positions are withheld because at least one result lacks explicit independent provenance or a documented evaluation scope. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

1. Claude Sonnet 4

   anthropic/claude-sonnet-4

   53.820598006644516%

   View modelEvidence aggregated