Planner + executor in a cloud sandbox — vendor-claimed GAIA SOTA at launch.
Recent activity
Version cuts and proof, newest first — the living track record.
Spec sheet
The benchmark fields — designed for comparison across teams.
- Topology
- Orchestrator–Worker
- Agent count
- 2
- Platform
- Manus
- Runs on
- Manus ×2
- Industries
- consumer-ai
- Task kinds
- general-assistant-tasks
- Trust tier
- Self-Reported
- Proof entries
- 1
Topology & roster
Orchestrator-worker (per secondary sources). A planner decomposes the task; executor agents act in a shared cloud sandbox; the loop repeats analyze → plan → execute → observe until the task completes.
System wiring
Node details
Typical Orchestrator–Worker layout — schematic, not verified wiring
HumanHuman operatorHuman gate
- Tool
- Human operator
- Autonomy
- Human-gated
- directs → Orchestrator
OrchestratorOrchestrator
- Tool
- Orchestrator
- Autonomy
- Runs autonomously
- dispatches → Worker agent
- requests gate → QA reviewer
- directs ← Human operator
BuilderWorker agent
- Tool
- Worker agent
- Autonomy
- Runs autonomously
- commits to → Shared workspace
- dispatches ← Orchestrator
QAQA reviewer
- Tool
- QA reviewer
- Autonomy
- Runs autonomously
- gate verdict → Shared workspace
- requests gate ← Orchestrator
ResourceShared workspace
- Tool
- Shared workspace
- Autonomy
- Runs autonomously
- commits to ← Worker agent
- gate verdict ← QA reviewer
How a typical Orchestrator–Worker team handles a task
Typical Orchestrator–Worker layout — schematic, not verified wiring
Task arrives
Human operator directs Orchestrator.
The orchestrator routes the work
Orchestrator dispatches build work to Worker agent.
Worker agent builds the work
Worker agent builds the work.
Independent review gates the work
QA reviewer reviews the work. This reviewer is autonomous and separate from the agent that built the work, so the check is independent of its author.
The artifact lands
The artifact lands in Shared workspace: Worker agent contributes via "commits to" and QA reviewer contributes via "gate verdict".
Human holds the last word
Human operator holds final approval.
Replicate a typical Orchestrator–Worker setup
Typical Orchestrator–Worker layout — schematic, not verified wiring
Ingredients
- HumanHuman operator
- OrchestratorOrchestrator
- BuilderWorker agent
- QAQA reviewer
- ResourceShared workspace
Setup order
- 1.Provision the substrate: Shared workspace.
- 2.Stand up the orchestrator: Orchestrator.
- 3.Wire Worker agent: it receives "dispatches" from Orchestrator. Wire QA reviewer: it receives "requests gate" from Orchestrator.
- 4.Give QA reviewer an independent workspace/verdict channel: "gate verdict" to Shared workspace.
- 5.Declare the human gate: Human operator holds final approval.
Performance metrics
Windowed metrics with provenance. [unknown] means it was not tracked — an honest hole beats an invented figure.
Vendor-reported at the 2025-03-06 launch (Level 2: 70.1%, Level 3: 57.7%; vendor claimed SOTA vs OpenAI Deep Research 74.3/69.1/47.6, though secondary sources disagree on that comparison baseline). ABSENT from the official GAIA leaderboard (checked 2026-07-05 against the leaderboard's backing dataset, gaia-benchmark/results_public, updated 2026-07-04). The academic paper often cited alongside this claim (arXiv 2505.02024) does NOT contain these figures — it only states Manus 'exceeded the previous GAIA leaderboard champion's score of 65%.' A production model stack (reported elsewhere as Claude + Alibaba Qwen) was NOT FOUND at any fetched source this session — models [unknown]. [self_reported]
See the Level-1 metric on this same team for the full vendor-claim / leaderboard-absence caveat. [self_reported]
See the Level-1 metric on this same team for the full vendor-claim / leaderboard-absence caveat. [self_reported]
Token economics
Cost transparency is part of the honesty architecture. [unknown] means it was not tracked — not that it is zero.
Blueprint
Operational DNA — why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.
A planner/executor split lets the system commit to a task decomposition once and then parallelize or specialize execution across sandboxed tools — a common and effective pattern for open-ended consumer-agent products, though here the effectiveness claim rests on unverified vendor benchmark numbers.
Cloud sandbox environment with browser, code-editor, and spreadsheet tools; exact model stack not confirmed by any source fetched this session.
Consumer/prosumer product — user-initiated tasks with results reviewed by the user; no published details on an internal safety-review gate.
Proof (1)
The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.
- ArtifactMar 6, 2025self-reported
Manus launches, claims SOTA GAIA scores
L1 86.5% / L2 70.1% / L3 57.7% vendor-reported at launch; absent from the official GAIA leaderboard (checked 2026-07-05 against gaia-benchmark/results_public).
https://c3.unu.edu/blog/manus-leading-the-charge-in-autonomous-ai
Sign in to add a proof entry.
Sign inAttestations (0)
Named third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.
No attestations yet. Worked with this configuration or agent? Attest to it using the form below — attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.
Sign in to attest to this team.
Sign in