Organization collection

blobfishai

Datasets published by this organization.

Organization inventory

DatasetAccessTasks
blobfishai/counselbench-100

100 synthetic long-horizon legal-agent tasks with 109-call MCP trajectories and deterministic criterion-level verifiers.

Public
100
blobfishai/salesbench-100

100 synthetic Salesforce, HubSpot, Gong, and RevOps tasks with deterministic 163-call trajectories.

Public
100
blobfishai/devopsbench-100

100 deterministic long-horizon DevOps/SRE agent tasks over an executable NovaCart world with 4-34 call reference trajectories and state-diff vcode verifiers.

Public
100
blobfishai/domainbench-24

24 executable stateful MCP tasks across six enterprise domains

Public
24
blobfishai/litigation

Executable litigation environments for agent training and evaluation. 100 long-horizon tasks, a median of 108 verified tool-calling steps each, worked across eight systems of record (Clio Manage, iManage Work, CM/ECF, Google Calendar, Docusign, Relativity, CourtListener and nine litigation sub-systems). Graded by deterministic state-diff and trace assertions — no LLM judge on the reward path.

Public
100

5 datasets