Planner + executor pool + per-step verification — vendor-claimed 77.6% on GAIA.
Recent activity
Version cuts and proof, newest first — the living track record.
Spec sheet
The benchmark fields — designed for comparison across teams.
- Topology
- Pipeline
- Agent count
- 3
- Platform
- Leni (Dupple)
- Runs on
- Leni (Dupple) ×3
- Industries
- consumer-ai
- Task kinds
- general-assistant-tasks
- Trust tier
- Self-Reported
- Proof entries
- 1
Topology & roster
Pipeline / layered orchestration. Layer 1 (planner) decomposes the task; Layer 2 (executor pool) carries out steps using commodity tools; Layer 3 routes each step across Anthropic and OpenAI frontier models; a per-step verifier checks output before proceeding.
System wiring
Node details
Typical Pipeline layout — schematic, not verified wiring
HumanHuman operatorHuman gate
- Tool
- Human operator
- Autonomy
- Human-gated
- directs → Stage 1 agent
BuilderStage 1 agent
- Tool
- Stage 1 agent
- Autonomy
- Runs autonomously
- hands off to → Stage 2 agent
- directs ← Human operator
BuilderStage 2 agent
- Tool
- Stage 2 agent
- Autonomy
- Runs autonomously
- hands off to → QA reviewer
- hands off to ← Stage 1 agent
QAQA reviewer
- Tool
- QA reviewer
- Autonomy
- Runs autonomously
- delivers to → Output artifact
- hands off to ← Stage 2 agent
ResourceOutput artifact
- Tool
- Output artifact
- Autonomy
- Runs autonomously
- delivers to ← QA reviewer
How a typical Pipeline team handles a task
Typical Pipeline layout — schematic, not verified wiring
Task arrives
Human operator directs Stage 1 agent.
The builders execute
Stage 1 agent and Stage 2 agent build 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 Output artifact: QA reviewer contributes via "delivers to".
Human holds the last word
Human operator holds final approval.
Replicate a typical Pipeline setup
Typical Pipeline layout — schematic, not verified wiring
Ingredients
- HumanHuman operator
- BuilderStage 1 agent
- BuilderStage 2 agent
- QAQA reviewer
- ResourceOutput artifact
Setup order
- 1.Provision the substrate: Output artifact.
- 2.Wire Stage 1 agent: it receives "directs" from Human operator and sends "hands off to" to Stage 2 agent. Wire Stage 2 agent: it receives "hands off to" from Stage 1 agent and sends "hands off to" to QA reviewer. Wire QA reviewer: it receives "hands off to" from Stage 2 agent.
- 3.Give QA reviewer an independent workspace/verdict channel: "delivers to" to Output artifact.
- 4.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.
128/165 on GAIA validation, claimed first place globally, per a single Dupple vendor blog (2026-05). ABSENT from the official GAIA leaderboard (checked 2026-07-05 against gaia-benchmark/results_public). Vendor's own comparison table claims: Genspark 75.4%, Manus 73.4%, OpenAI Deep Research 67.4% — but these rival scores conflict with those vendors' own self-reported figures elsewhere in this same batch (e.g. Genspark's own vendor claim is 87.8%, not 75.4%), and Dupple discloses no methodology for how it obtained them — do not treat this comparison table as a neutral/independent benchmark. Vendor claims the full +17-point uplift over a bare frontier model ('bare Opus 4.6 with tools: ~60%') is attributable to the architecture, with the biggest edge on Level-3 tasks. Single-source, no independent confirmation located this session. Source: dupple.com/blog/how-leni-beat-genspark-and-manus-on-gaia-benchmark, 2026-05. [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.
Per-step verification is the vendor's own explanation for most of the claimed uplift over a bare frontier model — catching errors immediately after each step, rather than only at the end of a long trajectory, bounds how far a single mistake can propagate before it's caught.
Production system prompt (unmodified for the benchmark claim), commodity tools, cross-provider model routing across Anthropic and OpenAI frontier models, no fine-tuning.
Consumer product — user-initiated tasks; per-step verification is an automated architectural layer, not a human review gate.
Proof (1)
The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.
- ArtifactMay 1, 2026self-reported
Dupple: Leni claims first place on GAIA validation
77.6% (128/165) claimed first place; absent from the official GAIA leaderboard (checked 2026-07-05); the vendor's rival comparison figures conflict with those vendors' own claims elsewhere in this batch.
https://dupple.com/blog/how-leni-beat-genspark-and-manus-on-gaia-benchmark
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