Submit your mixture for measurement
MoE model, mixture-of-models team, swarm, clan, council — if a group of models produces verdicts together, SwarmBench will measure what the group actually adds. Including when the answer is less than one.
What we need from you
Every member, with weights identity (hash or verifiable artifact reference). We join on weights, not names — a renamed model is a new model.
How a verdict is produced: router weights, voting rule, aggregation function. This is what delegation accuracy and consensus robustness are measured against.
You agree to the frozen-split law: practice items are visible, held-out items are never exported, the anti-Goodhart salt re-splits between generations.
The measurement contract
- We publish with CI and harness. Scores ship with 95% confidence intervals, coverage fields (measured / unparseable / UNMEASURED), the exact harness version, and the corpus anchor hash. No number without provenance.
- You get a signed attestation. Every completed measurement is sealed via the live trust spine (
os.meok.ai/api/sign, verifiable atos.meok.ai/api/verify) — a signed attestation of what was measured, when, and against which corpus root. - Negative results publish too. If your council measures n_eff below its seat count, that is the finding. It joins the Illusion Index next to ours. You can withdraw before publication; you cannot edit after.
Credits
Estate credits ladder. No checkout is wired on this page — measurement slots are arranged through the honest contact route, and the credits framing below is the current structure, not a paywall:
Open-source mixtures measured in the public batch as lanes open. Results public, attribution to the submitter.
Scheduled measurement window, full six-lane report, signed attestation included.
Per-run credits for repeated measurement (regression tracking across your mixture's versions).
Status note: the credits ladder is the estate's current framing. Payment rails are being wired; until then all intake runs through the contact route below. Nothing on this page charges you.
Start
Open a measurement conversation through the CSOAI connect route — mention SwarmBench, your member count, and your weights references:
Agents: the machine-readable submission contract is in /agent.json and /llms.txt.