💬 Banter, as the auditors found it. Provider →
last audit 7 Nov · evidence checked on-chainno check counts now
Approved auditors check that each provider serves the model it sells.
Approved auditors check that each provider serves the model it sells.
No check counts now. Last audited 7 Nov.
| Model | Differed↑ | × noise | Fail line | Noise | Proof |
|---|---|---|---|---|---|
| GPT-6.1 SolSAME 7 Nov · expired · auditors split: 1 DIFF, 1 SAME | 0% | 0.0× | 12 under | 0.0% | ↗ |
| Gemini 4 ArgonSAME 7 Nov · expired | 1% | 1.0× | 13 under | 1.0% | ↗ |
| Claude Sonnet 5.5SAME 7 Nov · expired | 1% | 0.5× | 16 under | 2.0% | ↗ |
| Kimi K3.1 ProSAME 7 Nov · expired | 3% | 0.3× | 27 under | 8.2% | ↗ |
| Claude Opus 5.5SAME 7 Nov · expired | 3% | 6.0× | 9 under | 0.0% | ↗ |
| GPT-6 AstraSAME 7 Nov · expired | 5% | 1.0× | 19 under | 5.5% | ↗ |
| Kimi K3SAME 7 Nov · expired | 7% | 0.8× | 26 under | 8.7% | ↗ |
| Claude Fable 5.1SAME 7 Nov · expired | 8% | 1.5× | 16 under | 5.5% | ↗ |
| GLM 5.3SAME 4 Nov · expired | 13% | 1.4× | 11 under | 9.4% | ↗ |
| Qwen 3.8 27BSAME 7 Nov · expired | 17% | 1.9× | 10 under | 8.8% | ↗ |
| MiniMax M3DIFF 7 Nov · expired | 50% | 3.1× | +29 over | 16.1% | ↗ |
85 of 170 differed (fails from 56) · 79 of 170 differed (fails from 52) · the real model differs from itself on 16%
Reasoning switched off with disable thinking, as the real model was asked.
| Round | Passed | Failed | Multiplier |
|---|---|---|---|
| 7 Novepoch 30 | 9 | 1 | ×1.16 |
| 4 Novepoch 29 | 8 | 0 | ×1.16 |
Audited by approved auditors · evidence on IPFS, hash-checked on-chain.