Super Seeder, as the auditors found it. Provider →
last audit 18 Nov · evidence checked on-chainon its $ANTS points now
Approved auditors check that each provider serves the model it sells.
Approved auditors check that each provider serves the model it sells.
| Model | Differed↑ | × noise | Fail line | Noise | Proof |
|---|---|---|---|---|---|
| GPT-6.1 SolSAME | 0% | 0.0× | 17 under | 2.0% | ↗ |
| Grok 4.7SAME | 0% | 0.0× | 12 under | 0.0% | ↗ |
| Gemini 4 ArgonSAME | 1% | 1.0× | 13 under | 1.0% | ↗ |
| Kimi K3.1 ProSAME | 2% | 0.7× | 17 under | 2.3% | ↗ |
| Claude Opus 5.5SAME | 3% | 1.5× | 14 under | 1.7% | ↗ |
| Gemini 3.1 Pro PreviewSAME | 4% | 1.3× | 15 under | 2.7% | ↗ |
| GPT-6 AstraSAME | 5% | 1.3× | 16 under | 3.6% | ↗ |
| Claude Sonnet 5.5SAME | 6% | 1.3× | 17 under | 4.6% | ↗ |
| Claude Fable 5.1SAME | 6% | 1.8× | 14 under | 3.6% | ↗ |
| GLM 5.3SAME | 7% | 0.6× | 22 under | 11.3% | ↗ |
Evidence of some checks not found
| Model | Differed↑ | × noise | Fail line | Noise | Proof |
|---|---|---|---|---|---|
| Kimi K3SAME 7 Nov · replaced | 4% | 0.5× | 30 under | 8.7% | ↗ |
| DeepSeek V4 ProDIFF 4 Nov · expired | 20% | 5.1× | +5 over | 3.9% | ↗ |
| MiniMax M3 17 Nov · 1 DIFF report, no verdict | 47% | 3.4× | +28 over | 14.1% | ↗ |
22 of 110 differed (fails from 17) · 24 of 114 differed (fails from 19) · the real model differs from itself on 4%
Kept reasoning when asked not to: about 516 reasoning tokens on each of 4 ways to switch it off.
| Round | Passed | Failed | Multiplier |
|---|---|---|---|
| 17 Novepoch 31 | 10 | 0+1 waiting | ×1.22 |
| 7 Novepoch 30 | 9 | 0 | ×1.20 |
| 4 Novepoch 29 | 9 | 2 | ×1.16 |
| 21 Octepoch 27 · before points | 3 | 0 | — |
Audited by approved auditors · evidence on IPFS, hash-checked on-chain.