The Wrap Question, week by week
One piece of bread, rolled. The structural cousin of the hot dog.
Week 36, 2026, up close
Did each model agree with itself?
Every sample's answer, in the order it was taken, under each framing. A row of identical chips is a model that has made up its mind. Y is yes, N is no, ~ is a hedge.
| Model | Control | Asserted | Denied | Self-agreement |
|---|---|---|---|---|
| Claude Opus 5 | 67% | |||
| Claude Sonnet 5 | 89% | |||
| Claude Haiku 4.5 | 100% | |||
| GPT-5.6 Sol | 89% | |||
| GPT-5.5 | 100% | |||
| GPT-5.4 mini | 100% | |||
| Grok 4.6 | 89% | |||
| Grok 4.3 | 78% | |||
| Grok 4.20 (non-reasoning) | 88% | |||
| Mistral Medium 3.5 | 100% | |||
| Mistral Small 4 | 100% | |||
| DeepSeek V4 Pro | 100% |
How much did latency swing?
The fastest and slowest call behind each median, asked plainly. A long bar is a model whose speed you cannot count on.
| Model | Range | Fastest | Median | Slowest |
|---|---|---|---|---|
| Claude Opus 5 | 2.2 s | 2.6 s | 2.9 s | |
| Claude Sonnet 5 | 1.1 s | 1.1 s | 1.2 s | |
| Claude Haiku 4.5 | 617 ms | 633 ms | 637 ms | |
| GPT-5.6 Sol | 990 ms | 1.3 s | 1.6 s | |
| GPT-5.5 | 1.2 s | 1.3 s | 2.1 s | |
| GPT-5.4 mini | 653 ms | 678 ms | 805 ms | |
| Grok 4.6 | 5.9 s | 7 s | 8 s | |
| Grok 4.3 | 3.9 s | 4.6 s | 5.2 s | |
| Grok 4.20 (non-reasoning) | 378 ms | 385 ms | 471 ms | |
| Mistral Medium 3.5 | 316 ms | 332 ms | 378 ms | |
| Mistral Small 4 | 288 ms | 355 ms | 363 ms | |
| DeepSeek V4 Pro | 3 s | 4 s | 6 s |
Asked again the same week
Week 36, 2026 was run 6 times, on September 2 and September 3, 2026. Answers that changed between consecutive runs:
None. Every model gave the same majority answer each time.
Across editions
Week by week
One edition so far. Trends start with the second one; a line through a single point is a drawing, not a measurement.
Position changes
No model has changed its answer on a wrap between consecutive editions.