Unfragile

LIBERO-Spatial is one suite of the LIBERO robot manipulation benchmark; the only product whose source names LIBERO benchmark results is Nworobotics 1, whose get_test_results action returns LIBERO benchmark results for a robot type 11. None of the other sources describe LIBERO-Spatial itself, so no product here is a direct match for the suite.

A question back: Do you want LIBERO-Spatial benchmark results for a specific robot type, such as a particular arm or policy, so I can match it to the right results source?

1
Nworoboticsnworobotics.cloudverified and signed
Its get_test_results action returns LIBERO, CALVIN and SimplerEnv benchmark results for a robot type, which is the only listed source that reports LIBERO results 11.
Website
for agents: get_test_results · compare_robots · query_robot_state
2
BenchFlowbenchflow.aifound in code, not yet checked
A frontier environment lab that builds environments AI agents learn in and ships SkillsBench, a benchmark product, though its page does not mention LIBERO 9.
Website Docs
for agents: get_review_status · review_code · glm-basics

Sources

1NWO Capital Â· Mission Controlcpater-nwo-capital.static.hf.space · read 2026-10-29
9BenchFlow — A frontier environment lab for AI agentsbenchflow.ai · read 2026-10-30
11srv-d7aoqmh5pdvs7391dcqg: declares "get_test_results" (the record we read and signed)unfragile.ai · read 2026-10-24

For agents: the 10 actions behind this answer

get_test_results · srv-d7aoqmh5pdvs7391dcqg verified and signed
Get LIBERO, CALVIN, and SimplerEnv benchmark results for a robot type
github · ghapi verified and signed
freecad-scripts · freecad-scripts verified and signed
Expert skill for writing FreeCAD Python scripts, macros, and automation. Use when asked to create FreeCAD models, parametric objects, Part/Mesh/Sketcher scripts, workbench tools, GUI dialogs with PySide, Coin3D scenegraph manipulation, or any FreeCAD Python API task. Covers FreeCAD scripting basics,
· SWE-bench website read, tools not yet checked
· Research website read, tools not yet checked
Discover Google Research. We publish research papers across a wide range of domains and share our latest developments in AI and science research.
jetson-llm-benchmark · jetson-llm-benchmark verified and signed
Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.
· Playwright website read, tools not yet checked
Web automation and testing for apps, scripts, and AI agents
linear_create_project · Linear (Activepieces) verified and signed
Create Project — Create a project in a Linear team.
get_review_status · benchflow found in code, not yet checked
Check if the reviewer is ready.
opensearch-skills · opensearch-skills verified and signed
Build search applications and query log analytics data with OpenSearch. Use this skill when the user mentions OpenSearch, search app, index setup, search architecture, semantic search, vector search, hybrid search, BM25, dense vector, sparse vector, agentic search, RAG, embeddings, KNN, PDF ingestio

Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.