# Which Claude model is the most consistent day to day?

**As of 2026-09-04, over the last 4 runs opus-5 changed its pass count 3 times, the most of any tracked model; haiku-4-5, fable-5, fable-5-1 did not move at all.**

## Last 5 readings

| Run | haiku-4-5 | sonnet-5 | opus-5 | fable-5 | fable-5-1 |
|---|---:|---:|---:|---:|---:|
| 2026-09-04 | 11/12 | 12/12 | 12/12 | 12/12 | 12/12 |
| 2026-09-03 | 11/12 | 12/12 | 12/12 | 12/12 | 12/12 |
| 2026-09-02 | 11/12 | 11/12 | 10/12 | - | - |
| 2026-09-01 | 11/12 | 12/12 | 11/12 | - | - |
| 2026-08-31 | 11/12 | 12/12 | 12/12 | - | - |

How this is measured: the same versioned battery, every tracked model, every morning, frozen request shape, deterministic scoring. https://winthropic.com/methodology.md

Cite: Winthropic Index, "Which Claude model is the most consistent day to day?", reading of 2026-09-04, https://winthropic.com/claude-model-consistency

Winthropic is an independent measurement project and is not affiliated with, endorsed by, or connected to Anthropic. Paying for output you are not getting? https://winthropic.com/audit.md prices your actual spend from a usage export; the summary is free.