🐜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

Phala, as the auditors found it. Provider →

last audit 17 Nov · evidence checked on-chain
×1.06

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
0
DIFF
Last audit
17 Nov
epoch 31 · counts to 32
By model
ModelDiffered↑× noiseFail lineNoiseProof
Kimi K3.1 ProSAME2%0.7×17 under2.3%↗
GLM 5.3SAME18%1.6×14 under11.3%↗

Evidence of some checks not found

2 older checks · 1 failed · not counting now
ModelDiffered↑× noiseFail lineNoiseProof
Kimi K3SAME 7 Nov · replaced7%0.8×26 under8.7%↗
Qwen 3.8 27BDIFF 7 Nov · expired21%2.6×+13 over7.9%↗
Qwen 3.8 27BDIFFno longer counts

47 of 160 differed (fails from 38) · 71 of 340 differed over 2 sets (fails from 58) · the real model differs from itself on 8%

Where it missed
Astronomy (periods and distances)7/13
Medical (drug half-lives)8/17
Biology (chromosome numbers)10/23
Cryptography (parameters)5/12
For example
Angular diameter in arcseconds of Andromeda Galaxy M31real 178 · provider 10,680
Number of shots in the long take of Birdman or (The Unexpected Virtue of Ignorance)real 1 · provider 39
Number of original BGP version numbersreal 1 · provider 4

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

audited 7 Nov, 22:33 UTC · epoch 30
test power 91% · median answer 12.3 s · 2 audits
Audit rounds
RoundPassedFailedMultiplier
17 Novepoch 3120×1.02
7 Novepoch 3021×1.02
4 Novepoch 2910×1.02

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