Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-08-08 · source-backed
DataSpace benchmarks data agents on 410 cross-language tasks over 7,439 artifacts totaling 15.01GB across CSV, JSON, SQLite, Markdown, PDF and video, validated by 11 domain experts. Six frontier multimodal models across five frameworks: best accuracy only 66.34%, and harness choice alone produced a 15.36-point spread independent of model. The consistent failure across all six backbones was multimodal evidence integration and joins, which is precisely what every "chat with your data" product claims to do.
Each link below shares sources, entities, or timing with this story.
OpenClaw uses SQLite / Shared entity: PDF / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (OpenClaw uses SQLite); both cover PDF; reported by the same outlet (arxiv.org).
OpenClaw uses SQLite / Shared entity: SQLite / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (OpenClaw uses SQLite); both cover SQLite; reported by the same outlet (arxiv.org).
Shared entities / Shared topic / Earlier coverage
Both cover CSV, Markdown, PDF; overlapping topics (agent, benchmark); earlier CSV coverage from 2026-08-06.
mempalace uses SQLite / Shared entity: SQLite / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (mempalace uses SQLite); both cover SQLite; overlapping topics (agent, benchmark).
OpenClaw uses SQLite / Shared entity: Markdown / Shared topic / Earlier coverage
Linked by a graph relationship (OpenClaw uses SQLite); both cover Markdown; overlapping topics (agent, data, harness).
Shared entity: JSON / Same source domain / Shared topic / Earlier coverage / Tension
Both cover JSON; reported by the same outlet (arxiv.org); overlapping topics (agent, choice, model).
Shared entity: Markdown / Same source domain / Shared topic / Earlier coverage
Both cover Markdown; reported by the same outlet (arxiv.org); overlapping topics (agent, benchmark, chat, model).
Shared entity: PDF / Same source domain / Shared topic / Earlier coverage / Tension
Both cover PDF; reported by the same outlet (arxiv.org); overlapping topics (agent, model).