Models · Claude
Claude Sonnet 4.6
Asked for a few hundred random integers, Claude Sonnet 4.6 does not pick evenly. This page is the shape of that preference, built from 36 recorded answers containing 10755 numbers, and it is what the identify tool compares a pasted reply against.
- Bank id
claude-sonnet-4-6- Family
- Claude
- Collected through
- API
- Collected on
- Not recorded upstream
- Status
- Inherited from ModelTrace; serving identity not independently verified
- Distinct values used
- 353 of 355
- Prompt environments
- 12 of 12
Capability and price
- Sold by
- Anthropic
- Intelligence index
- 25 · v4.3.2, scored as non-reasoning, high effort
- Index rank
- Not ranked — the index marks this configuration superseded by Claude Sonnet 5.
- Input, per 1M tokens
- 3.00
- Output, per 1M tokens
- 15.00
- Blended, per 1M tokens
- 6.00
- Price rank
- Not ranked
- Context window
- 1,000,000 tokens
Read on 2026-10-02, not measured here: index page · price page
Distribution
Selected number 38
| Model | Times chosen | Share |
|---|---|---|
| Claude Sonnet 4.6 | 72 | 0.67% |
Favourite numbers
| Number | Times chosen | Share |
|---|---|---|
| 38 | 72 | 0.67% |
| 88 | 67 | 0.62% |
| 67 | 65 | 0.60% |
| 83 | 62 | 0.58% |
| 74 | 61 | 0.57% |
| 47 | 60 | 0.56% |
| 93 | 60 | 0.56% |
| 84 | 59 | 0.55% |
| 57 | 58 | 0.54% |
| 73 | 58 | 0.54% |
| 312 | 58 | 0.54% |
| 341 | 58 | 0.54% |
How reliably it is recognised
In held-out testing across all twelve prompt environments, 11 of 12 three-answer runs named this model with a clear margin, 0 were close calls inside its family, 1 had only a weak match, and 0 named a different model with a clear margin.
With this model removed from the bank and its own answers scored against the rest, 0 of 12 runs still named another model with a clear margin, 0 were close calls inside the family, and 12 had only a weak match. Its answers landed most often on Claude Opus 4.6 (6 of 12). That is the number to keep in mind if you are testing a version that is not listed here.
Both measurements count the status the site attaches to the first-ranked model, not the bare ranking alone. The methodology page explains how they were made and what they leave out.