benchmarks.wiki / Public workspace

AutoGPT (GPT4 backend)

All models · Read as JSON

These are quotations of published scores, not measurements made here. Evaluation conditions differ by row, so this is not a ranking. Different metrics must not be combined.

Recorded benchmark reports
BenchmarkScoreMetricSetupReported bySource
GAIAAutoGPT (GPT4 backend)14.4Score in %Level 1 (146 questions).PaperReported: Not statedTable 4, Level 1 scoreChecked: 2026-09-16