🐜AntSeedStats
HomeNetworkModelsProvidersStakingFree AI$ANTS

Explore

OverviewRevenueProvidersBuyersModelsDistributionStakingRewardsDIEM$ANTSChannelsTransactionsLabs

Project

AboutFAQDevelopersFor agentsChangelogStatus

Antseed

WebsiteDownload Antseed DesktopDocsGitHubX (@antseedai)Telegram
🐜AntSeedStats
The metrics and intelligence layer of the Antseed ecosystem.
Built by @gekko_eth
AntSeedStats is an independent, community-built dashboard, not officially affiliated with the Antseed team. All data is sourced on-chain and from public endpoints.

Model checks

STEYG, as the auditors found it. Provider →

last audit 18 Nov · evidence checked on-chain
×1.02

on its $ANTS points now

How this works (Antseed's announcement ↗)

Approved auditors check that each provider serves the model it sells.

  • 🧪They buy from it like any buyer: ~100 obscure number questions, compared with the real model.
  • 📏The real model misses some too: that is the noise. A provider fails only if it misses clearly more, and two auditors must agree.
  • 💰Each pass +2% on $ANTS points, up to +50%. Fails cost more: 1 −4%, 2 −16%, 3 −36%. Checked again every week.
How this works (Antseed's announcement ↗)

Approved auditors check that each provider serves the model it sells.

  • 🧪They buy from it like any buyer: ~100 obscure number questions, compared with the real model.
  • 📏The real model misses some too: that is the noise. A provider fails only if it misses clearly more, and two auditors must agree.
  • 💰Each pass +2% on $ANTS points, up to +50%. Fails cost more: 1 −4%, 2 −16%, 3 −36%. Checked again every week.
Passed
3
SAME · counting now
Failed
1
DIFF
Last audit
18 Nov
epoch 31 · counts to 32
By model
ModelDiffered↑× noiseFail lineNoiseProof
Claude Opus 5.5SAME1%0.5×16 under1.7%↗
Claude Sonnet 5.5SAME7%1.5×16 under4.6%↗
GPT-6.1 SolSAME8%4.0×9 under2.0%↗
GPT-6 AstraDIFF13%4.7×+3 over2.7%↗
Why it failed
GPT-6 AstraDIFF

28 of 220 differed over 2 sets (fails from 25) · 17 of 100 differed (fails from 14) · the real model differs from itself on 3%

Where it missed
Physics (material properties)6/9
Chinese internet (platform dates)12/27
Chinese geography (measurements)6/17
Chemistry (boiling points)1/3
For example
The Middleman — “The Accidental Occidental Conception” — season 1 episode number (one-based episode count)real 2 · provider 9
Coqên County, Tibet — administrative area (square kilometres)real 22,980 · provider 98,192
Fujian Province Songxi County administrative area (square kilometres, rounded to nearest integer)real 1,040 · provider 3,104

✓Reasoning switched off with reasoning effort none, as the real model was asked.

audited 18 Nov, 18:14 UTC · epoch 31
test power 97% · median answer 11.7 s · 2 audits
Audit rounds
RoundPassedFailedMultiplier
17 Novepoch 3131×1.02
7 Novepoch 3020×1.04
4 Novepoch 2920×1.04

Audited by approved auditors · evidence on IPFS, hash-checked on-chain.