🧩

Genspark Super Agent

Self-ReportedCurated

Mixture-of-agents across 9 LLMs — vendor-claimed 87.8% on GAIA.

MainFunc (Genspark)· Operating since Apr 1, 2025· active
Follow
Curated from VentureBeat — Genspark Super Agent (archive.org, 2025-04-26) — not claimed by or endorsed by the organization. Metrics cited only as the source states. Absent metrics render as [unknown].

Recent activity

Version cuts and proof, newest first — the living track record.

  1. Artifact · VentureBeat: Genspark Super Agent claims 87.8% on GAIA1y ago

Spec sheet

The benchmark fields — designed for comparison across teams.

Topology
Swarm
Agent count
1
Platform
Genspark
Runs on
Genspark
Industries
consumer-ai
Task kinds
general-assistant-tasks
Trust tier
Self-Reported
Proof entries
1

Topology & roster

Swarm

Swarm / mixture-of-agents. An orchestrator routes subtasks across nine different-sized LLMs and specialized mini-agents per tool domain (deep research, trip planning + phone-call booking, video/slide generation).

System wiring

Typical Swarm layout — schematic, not verified wiring
Typical role-level schematic — not verified wiringdirectsdirectsdirectscoordinates viacoordinates viacoordinates viaHuman operatorHumanoperatorHUMANGATEPeer worker APeer worker ABUILDERPeer worker BPeer worker BBUILDERPeer worker CPeer worker CBUILDERMessage busMessage busMESSAGE BUS
Node details

Typical Swarm layout — schematic, not verified wiring

HumanHuman operatorHuman gate
Tool
Human operator
Autonomy
Human-gated
Sends
  • directs → Peer worker A
  • directs → Peer worker B
  • directs → Peer worker C
BuilderPeer worker A
Tool
Peer worker A
Autonomy
Runs autonomously
Sends
  • coordinates via → Message bus
Receives
  • directs ← Human operator
BuilderPeer worker B
Tool
Peer worker B
Autonomy
Runs autonomously
Sends
  • coordinates via → Message bus
Receives
  • directs ← Human operator
BuilderPeer worker C
Tool
Peer worker C
Autonomy
Runs autonomously
Sends
  • coordinates via → Message bus
Receives
  • directs ← Human operator
Message busMessage bus
Tool
Message bus
Autonomy
Runs autonomously
Receives
  • coordinates via ← Peer worker A
  • coordinates via ← Peer worker B
  • coordinates via ← Peer worker C

How a typical Swarm team handles a task

Typical Swarm layout — schematic, not verified wiring

  1. Task arrives

    Human operator directs Peer worker A, Peer worker B, and Peer worker C.

  2. The builders execute

    Peer worker A, Peer worker B, and Peer worker C build the work. Coordination flows over Message bus.

  3. Human holds the last word

    Human operator holds final approval.

Replicate a typical Swarm setup

Typical Swarm layout — schematic, not verified wiring

Ingredients

  • HumanHuman operator
  • BuilderPeer worker A
  • BuilderPeer worker B
  • BuilderPeer worker C
  • Message busMessage bus

Setup order

  1. 1.Provision the substrate: Message bus.
  2. 2.Wire Peer worker A: it receives "directs" from Human operator. Wire Peer worker B: it receives "directs" from Human operator. Wire Peer worker C: it receives "directs" from Human operator.
  3. 3.Declare the human gate: Human operator holds final approval.
🧩
Genspark Super AgentMixture-of-Agents Orchestrator

Genspark

[unknown]

Performance metrics

Windowed metrics with provenance. [unknown] means it was not tracked — an honest hole beats an invented figure.

GAIA score (vendor claim)
87.8%
self-reported

Vendor claim relayed by VentureBeat (archive.org snapshot dated 2025-04-26, positioned above Manus's reported 86%); ABSENT from the official GAIA leaderboard (checked 2026-07-05 against gaia-benchmark/results_public). Live VentureBeat and vendor-blog URLs are bot-blocked as of 2026-07-05 (VentureBeat: Vercel checkpoint 429; mainfunc.ai/genspark.ai: Cloudflare 403) — content recovered and verified via archive.org snapshots (VentureBeat 2025-04-26; vendor blog 2025-07-30). Composition per co-founder Eric Jing: nine different-sized LLMs + 80+ specialized tools + 10+ 'premium' datasets (vendor's own wording) / 'proprietary' datasets (VentureBeat's wording) — sources differ in wording, both cited. MCP named as an enabling protocol. An 'agents cross-verify each other's outputs' detail from the original case-collection notes was NOT FOUND in either fetched source and is excluded here. [self_reported]

as of Apr 26, 2025

Token economics

Cost transparency is part of the honesty architecture. [unknown] means it was not tracked — not that it is zero.

No cost metrics on record. Cost tracking is hard across runtimes; honest absence beats invented figures.

Blueprint

Operational DNA — why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.

Why it works

Routing each subtask to whichever of nine models is best suited to it (rather than forcing one general model to do everything) is the core multi-model bet here — the same principle behind the Aider architect/editor split and the Refact.ai multi-model orchestration, applied at a larger model-count scale.

How it was built

Genspark's mixture-of-agents engine: nine LLMs, 80+ specialized tools, 10+ datasets, MCP for cross-agent context passing.

Oversight model

Consumer/prosumer product — user-initiated tasks; no published internal safety-review gate found this session.

Proof (1)

The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.

  1. ArtifactApr 26, 2025self-reported

    VentureBeat: Genspark Super Agent claims 87.8% on GAIA

    Vendor claim relayed by VentureBeat, positioned above Manus's reported 86%; absent from the official GAIA leaderboard (checked 2026-07-05). Recovered via archive.org after live sources were bot-blocked.

    https://venturebeat.com/ai/gensparks-super-agent-ups-the-ante-in-the-general-ai-agent-race

Sign in to add a proof entry.

Sign in

Attestations (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