Is Claude Code down or slower today?
As of · an hourly probe of Claude Code (Claude Opus 5.5) and Claude Code (Claude Sonnet 5.5) on the Claude Max subscription, one account, from one EU server · not an official status page
Claude Code on the Claude Max subscription: answering
Last hourly probe — Claude Opus 5.5: answered in 14.4 s at 13:37 UTC · Claude Sonnet 5.5: answered in 11.6 s at 13:37 UTC
Is Claude Code answering on the Claude Max subscription right now? With Claude Opus 5.5: yes — our last probe, at 13:37 UTC, answered in 14.4 s; 0 of 24 calls failed in the last 24 hours. With Claude Sonnet 5.5: yes — our last probe, at 13:37 UTC, answered in 11.6 s; 0 of 2 calls failed in the last 24 hours. This is an hourly probe of one account from one EU server, not a status page: it can miss an outage between probes and does not see problems that hit other accounts or regions. Is Claude Code slower today? Claude Code (Claude Opus 5.5) generated 115.8 tokens/s over the last 24 hours vs 113.6 tokens/s in the 7 days before (+2%) — no significant change (p=0.00475). Claude Code (Claude Sonnet 5.5): measuring, 2 samples in the last 24 hours; no verdict until the 7-day baseline is in.
Also: Codex vs Claude Code, side by side · all coding agents · Is Codex down or slower today? · Is Antigravity CLI down or slower today?
Is Claude Code slower today?
Each model is compared only with its own last 7 days on one fixed task with a single exact answer.
Claude Code · Claude Opus 5.5: no significant change in the last 24 hours
Last measured 2026-11-11 13:37 UTC · claude-cli 2.1.322 (Claude Code) · effort high · Claude Max subscription · errors in 24 h: 0% · served model claude-opus-5-5 as reported by the CLI (0 mismatches in 7 days)
| Metric | Last 24 h | 7 days before | Change | Verdict |
|---|---|---|---|---|
| Speed | 115.8 tokens/s | 113.6 | +2% | no significant change (p=0.00475) |
| Thinking | 764 tokens | 862 | −11% | no significant change (p=0.103) |
| First token | 2.3 s | 2.6 s | −11% | no significant change (p=0.00829) |
Claude Code · Claude Sonnet 5.5: measuring — the 7-day baseline is still filling up
Last measured 2026-11-11 13:37 UTC · claude-cli 2.1.322 (Claude Code) · effort high · Claude Max subscription · errors in 24 h: 0% · served model claude-sonnet-5-5 as reported by the CLI (0 mismatches in 7 days)
| Metric | Last 24 h | 7 days before | Change | Verdict |
|---|---|---|---|---|
| Speed | — tokens/s | — | — | measuring, no verdict yet |
| Thinking | — tokens | — | — | measuring, no verdict yet |
| First token | — | — | — | measuring, no verdict yet |
Speed is output tokens (thinking included) per second of response time. A change counts as significant only when the median moves by at least 15% and a Mann-Whitney test gives p < 0.01, with at least 12 recent and 48 baseline samples. These numbers are not comparable with other agents: Claude Code reports API time while Codex and Antigravity CLI report turn time, Antigravity CLI does not stream thinking, and the tokenizers differ, so the same number means different things.
Hourly speed, last 7 days
Claude Code · Claude Opus 5.5
Claude Code · Claude Sonnet 5.5
Daily medians
| UTC day | Claude Opus 5.5 tokens/s | thinking | Claude Sonnet 5.5 tokens/s | thinking |
|---|---|---|---|---|
| 2026-11-11 | 116.4 | 806 | 121.6 | 635 |
| 2026-11-10 | 115.2 | 777 | — | — |
| 2026-11-09 | 114.9 | 898 | — | — |
| 2026-11-08 | 114.6 | 900 | — | — |
| 2026-11-07 | 110.5 | 858 | — | — |
| 2026-11-06 | 110.6 | 902 | — | — |
| 2026-11-05 | 111.6 | 828 | — | — |
| 2026-11-04 | 112.3 | 895 | — | — |
| 2026-11-03 | 113.8 | 839 | — | — |
| 2026-11-02 | 108.6 | 986 | — | — |
How long does Claude Code take to answer?
| Model | Median, 24 h | Median, 7 days | Failed, 24 h | Failed, 7 days |
|---|---|---|---|---|
| Claude Opus 5.5 | 15.2 s 24 runs | 15.7 s 167 runs | 0 of 24 | 0 of 167 |
| Claude Sonnet 5.5 | 10.4 s 2 runs, too few | 10.4 s 2 runs, too few | 0 of 2 | 0 of 2 |
End to end on our fixed task: from launching the CLI to the complete answer, by our own clock. The same task in the other agents: Codex vs Claude Code, side by side.
"Too few": not enough successful runs yet to compare with other agents. "Failed": calls that errored, timed out, were rate-limited or could not count as a clean measurement.
Has it got worse at hard questions?
- Claude Code (Claude Opus 5.5): last 7 days vs baseline -0.8 points ± 2.9 (z=-0.29, 78 questions) — no significant change.
- Claude Code (Claude Sonnet 5.5): the hard panel has not run yet.
A fixed panel of hard questions, judged against each model's own baseline; details on all coding agents.
Is this the official status?
No. This is an hourly probe of one account from one EU server, not a status page: it can miss an outage between probes and does not see problems that hit other accounts or regions. The vendor's own incident reports: status.claude.com. The vendor's developer API, measured separately every 5 minutes from 4 regions: Is the Claude API (Anthropic) down? — access through the Claude Max subscription is a different service with its own limits, so the two can differ.
Questions
Is Claude Code down right now?
With Claude Opus 5.5: not on our account — our last probe, at 13:37 UTC, answered in 14.4 s; 0 of 24 calls failed in the last 24 hours. With Claude Sonnet 5.5: not on our account — our last probe, at 13:37 UTC, answered in 11.6 s; 0 of 2 calls failed in the last 24 hours. This is an hourly probe of one account from one EU server, not a status page: it can miss an outage between probes and does not see problems that hit other accounts or regions. For the vendor's own incident reports, see status.claude.com.
Is Claude Code slower today?
Claude Code (Claude Opus 5.5) generated 115.8 tokens/s over the last 24 hours vs 113.6 tokens/s in the 7 days before (+2%) — no significant change (p=0.00475). Claude Code (Claude Sonnet 5.5): measuring, 2 samples in the last 24 hours; no verdict until the 7-day baseline is in.
How long does Claude Code take to answer?
On our fixed task, end to end, Claude Code took a median of 15.2 s (24 runs) over the last 24 hours and 15.7 s (167 runs) over 7 days with Claude Opus 5.5; 10.4 s (2 runs, too few to compare) over the last 24 hours and 10.4 s (2 runs, too few to compare) over 7 days with Claude Sonnet 5.5. The same task in the other agents: Codex vs Claude Code, side by side.
Has Claude Opus 5.5 in Claude Code got worse at hard questions?
Claude Code (Claude Opus 5.5): last 7 days vs baseline -0.8 points ± 2.9 (z=-0.29, 78 questions) — no significant change.
Which model and plan does this page measure?
Claude Code with Claude Opus 5.5 (effort high); Claude Code with Claude Sonnet 5.5 (effort high), on the Claude Max subscription, CLI claude-cli 2.1.322 (Claude Code); one account, one EU server.
How it is measured
- What
- Claude Code with Claude Opus 5.5 (effort high); Claude Code with Claude Sonnet 5.5 (effort high); tools disabled or denied by permission policy, a fresh isolated session per call, on the Claude Max subscription.
- When
- every hour at :37 UTC, one fixed task per agent.
- Where
- one server in the EU (Hetzner, Germany); a single account per vendor.
- Errors
- a failed call is 'not measured', never a wrong answer.
- Data
- /api/coding-agents.json (JSON, CC BY 4.0) · markdown