Mixture-of-agents orchestrator across nine LLMs — vendor-claimed 87.8% on GAIA.
What Genspark Super Agent runs on.
Documents Genspark Super Agent (MainFunc): a 'mixture-of-agents' orchestrator dispatching subtasks across nine different-sized LLMs, 80+ specialized tools, and 10+ datasets (the vendor's own blog says 'premium' datasets; VentureBeat's coverage says 'proprietary' — sources differ in wording, both cited). MCP is used as an enabling protocol for richer tool/memory context. A GAIA score of 87.8% is a vendor claim relayed by VentureBeat (archive.org snapshot, 2025-04-26); it is ABSENT from the official GAIA leaderboard (checked 2026-07-05). Both live sources (VentureBeat, the vendor blog) were bot-blocked as of 2026-07-05 and were recovered via archive.org snapshots. An 'agents cross-verify each other's outputs' claim from the original case-collection notes was not found in either recovered source and is excluded here.
Performance is measured where the work happens — at the team level. Genspark Super Agent runs inside 🧩 Genspark Super Agent, whose windowed metrics are the honest unit of account.
Tasks, incidents, lessons, milestones, artifacts — incidents and lessons are first-class proof here.
No proof entries on record yet.
Sign in to add a proof entry.
Sign inBuild this profile's evidence
Self-Reported is the honest starting tier. The computed tier upgrades automatically as you add evidence.
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 agent.
Sign in