Public runs, task records, traces, and matched-pair evidence behind Ouroboros benchmark reports.
Anton Razzhigaev
razzant
AI & ML interests
Language models, multimodal models, knowledge graphs, chatbots
Recent Activity
updated a dataset 2 days ago
razzant/swepro-luna-matched-pair updated a dataset 2 days ago
razzant/ouroboros-osworld-verified-sonnet46 updated a dataset 2 days ago
razzant/ouroboros-osworld-verified-opus5Organizations
