Claude Code
Opus 5
Inside Claude Code we ask for claude-opus-5 every hour. Everything below comes from those runs on our lab machine.
Write speed, last 24 hours
35.0answer tok/s
6.89s typical total wait
Likely middle: 5.31s–7.35s
Visible answer tokens per second across the whole command. Hidden thinking does not make this number larger. Higher is faster. These are the middle values of 22 completed checks out of 24 scheduled in the last 24 hours.
- Time to first word
- 2.72s
- How long before the first visible word shows up. Lower is better.
- Typical total wait
- 6.89s
- How long the whole command took, start to finish, including the app booting. Lower is faster.
- Last ping
- —
- The newest tiny “reply ok” check. It measures wake-up time, not writing speed.
What stands out
Four facts pulled straight from the saved runs.
- Board position
- #4 of 10
- Just ahead: Sonnet 5 at 6.57s total wait. Just behind: Fable 5 at 7.79s total wait.
- Answered when scheduled
- 22/24
- Completed answers out of all scheduled checks in the last 24 hours.
- Served as
- claude-opus-5
- The model name the app reported back. If it differs from the pin, we say so.
- Round-to-round swing
- 2.0×
- How much the fastest round beat the slowest one. A big swing means a noisy day.
Recent rounds
Newest first. Fails stay in the list with their reason.
| When | Result | Writing speed | Total wait |
|---|---|---|---|
| 3m ago | overloadedclean | — | — |
| 1h ago | overloadedclean | — | — |
| 2h ago | okclean | 41.0 tok/s | 5.88s |
| 3h ago | okclean | 45.4 tok/s | 5.31s |
| 4h ago | okclean | 51.9 tok/s | 4.64s |
| 5h ago | okclean | 34.7 tok/s | 6.94s |
| 6h ago | okclean | 57.4 tok/s | 4.20s |
| 7h ago | okclean | 49.8 tok/s | 4.84s |
Read next
Its closest rival in Codex — same window, same units, with the leader marked on every row.
The pin next to it in Claude Code. See what the tier jump buys inside one app.
More models
How to read this
Every number here comes from our lab machine running the paid app, one try per hourly round. The live check uses test kit v0.2; recovered history appears only after its raw file passes the same visible-speed rules. Our measurements, not the vendor’s.