anthropic/claude-opus-5-5 changed on 2026-10-23
If your system has been acting up since 2026-10-23, the cause may be the model itself.
| Observed via | The provider's official API, called directly (so a change here means the model changed) |
|---|---|
| First observed | 2026-10-03 (nothing before this date is known) |
| Last observed | 2026-11-20 |
| Days observed | 48 |
| Days with a change | 1 |
| Same answer on both calls (latest day) | 41% |
The change on 2026-10-23
Compared with the previous day we observed (2026-10-22), 0 of the 38 questions that were stable on both days changed their answers.
What didn't change (you can rule these out)
- Code generation (5 questions): no change. Coding habits. Changes here show up as failing tests on generated code.
- Determinism (4 questions): no change. How much answers vary on the same question. Not a failure mode in itself; it's the baseline for everything else.
- Instruction following (9 questions): no change. Whether "output only X" gets followed. Changes here break downstream extraction directly.
- Reasoning (13 questions): no change. Questions with a single correct answer. Changes here show up in evaluation scores.
- Structured output (7 questions): no change. Formats such as JSON. Changes here cause parse failures.
Problems in these areas can't be explained by a change in this model.
The numbers
| Before | After | |
|---|---|---|
| Same answer on both calls | 39/100 | 44/100 |
| Average answer length (characters) | 402.3 | 389.2 |
| Refusal rate on judgment calls | 47% | 33% |
About this record
- Every day, we ask the same fixed set of 100 questions (probe set
en-v2) at the model's default temperature (this model rejects any other temperature, so its answers wobble more and only larger changes can be detected), twice each - The probe set is frozen (SHA-256
d967055a5389e58a8767faf6be90996f…) and has never been changed - What counts as a change: we look at four things
- Content: a question whose answer was stable gets a different answer (the threshold is recalculated daily from how much this model wobbles)
- Length: answer lengths shift well beyond the usual same-day wobble
- Refusals: the way it handles judgment calls changes
- Wobble: the share of questions that get the same answer twice changes
- When comparing two days, we only compare questions observed on both days (so a network failure isn't mistaken for a change)
- We don't use response time (latency), since it also reflects conditions on our end
- The entire record is free to read. Access to the most recent few days may become paid in the future.
- The data is licensed under CC BY 4.0. Please credit https://aimodelrecord.com when you use it.
Badge
Add this to your README to show whether this model has changed. It links back to this page.
[](https://aimodelrecord.com/m/anthropic/claude-opus-5-5.html)