Model checks
Open Bird, as the auditors found it. Provider →
last audit 18 Nov · evidence checked on-chain×1.02
on its $ANTS points now
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
Last audit
18 Nov
epoch 31 · counts to 32
| Model | Differed↑ | × noise | Fail line | Noise | Proof |
|---|
| Claude Opus 5.5SAME auditors split: 1 DIFF, 1 SAME | 1% | 1.0× | 14 under | 0.9% | ↗ |
| GPT-6 AstraSAME auditors split: 1 DIFF, 1 SAME | 3% | 3.0× | 11 under | 1.0% | ↗ |
| Kimi K3SAME | 8% | 2.0× | 13 under | 4.2% | ↗ |
| Claude Fable 5.1DIFF | 27% | 7.5× | +9 over | 3.6% | ↗ |
Claude Fable 5.1DIFF
30 of 110 differed (fails from 21) · 35 of 140 differed (fails from 27) · the real model differs from itself on 4%
Where it missed
Medical (drug half-lives)18/48
Astronomy (periods and distances)5/14
Chemistry (melting points)12/34
Biology (chromosome numbers)10/33
For example
M87 jet projected length in kiloparsecsreal 1.5 · provider 5
Henize 2-10 blue compact dwarf black hole mass in millions of solar massesreal 1 · provider 3
Qaidam Basin area (square kilometers)real 120,000 · provider 257,768
✓Reasoning switched off with reasoning effort none, as the real model was asked.
1 older check · not counting now
| Model | Differed↑ | × noise | Fail line | Noise | Proof |
|---|
| DeepSeek V4 Pro 7 Nov · expired · no verdict this round | 3% | 0.5× | 9 under | 6.7% | ↗ |
| Round | Passed | Failed | Not tested | Multiplier |
|---|
| 18 Novepoch 31 | 3 | 1 | 0 | ×1.02 |
| 7 Novepoch 30 | 4 | 0 | 1 | ×1.08 |
| 4 Novepoch 29 | 1 | 1 | 2 | ×1.04 |
| 21 Octepoch 27 · before points | 1 | 0 | 1 | — |