🐜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

Relay Works, as the auditors found it. Provider →

last audit 18 Nov · evidence checked on-chain
×1.14

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
9
SAME · counting now
Failed
1
DIFF
Last audit
18 Nov
epoch 31 · counts to 32
By model
ModelDiffered↑× noiseFail lineNoiseProof
GPT-6.1 SolSAME1%0.5×16 under2.0%↗
Claude Fable 5.1SAME2%0.5×19 under3.6%↗
Claude Opus 5.5SAME3%1.5×14 under1.7%↗
GPT-6 AstraSAME5%1.3×16 under3.6%↗
Claude Sonnet 5.5SAME6%1.3×17 under4.6%↗
Qwen 3.8 27BSAME9%0.8×29 under10.6%↗
MiMo V2.6 ProSAME10%0.8×28 under12.1%↗
GLM 5.3SAME17%1.5×17 under11.3%↗
MiniMax M3DIFF48%3.3×+31 over14.4%↗

Evidence of some checks not found

Why it failed
MiniMax M3DIFF

68 of 169 differed (fails from 52) · 86 of 180 differed (fails from 55) · the real model differs from itself on 14%

Where it missed
Medical (drug half-lives)19/24
Biology (chromosome numbers)9/12
Physics (material properties)14/22
Astronomy (periods and distances)5/9
For example
ml kem 512 decap secret bytesreal 32 · provider 1,632
freaks track countreal 1 · provider 12
talazoparib elimination half life hoursreal 15 · provider 90

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

audited 18 Nov, 18:14 UTC · epoch 31
test power 91% · median answer 1.0 s · 2 audits
2 older checks · not counting now
ModelDiffered↑× noiseFail lineNoiseProof
DeepSeek V4 Pro 7 Nov · expired · not tested · provider unreachable————↗
Kimi K3 7 Nov · replaced · not tested · provider unreachable————↗
Audit rounds
RoundPassedFailedNot testedMultiplier
17 Novepoch 31810×1.14
7 Novepoch 300011×1.02
4 Novepoch 29610×1.06
21 Octepoch 27 · before points501—

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