Codex
GPT-5.6 Sol
Inside Codex we ask for gpt-5.6-sol every hour. Everything below comes from those runs on our lab machine.
Write speed, last 24 hours
22.6wall tok/s
Tokens per second across the whole command — you press enter, the app starts, thinks, writes, finishes. Higher is better. This is the middle value of 33 clean rounds out of 33 tried in the last 24 hours.
- Time to first word
- —
- This app does not stream text, so we cannot time the first word.
- Middle wall time
- 10.8s
- 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
- #8 of 10
- Just ahead: GPT-5.5 at 24.7 wall tok/s. Just behind: GPT-5.6 Terra at 22.5 wall tok/s.
- Rounds that worked
- 33/33
- Clean rounds out of rounds tried, in the last 24 hours.
- Served as
- not echoed
- This app does not echo a model name back, so we cannot confirm it.
- Round-to-round swing
- 1.7×
- 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 | Wall tok/s |
|---|---|---|
| just now | okno tool items | 25.0 |
| 1h ago | okno tool items | 15.4 |
| 2h ago | okno tool items | 22.3 |
| 3h ago | okno tool items | 26.3 |
| 4h ago | okno tool items | 23.7 |
| 5h ago | okno tool items | 26.8 |
| 6h ago | okno tool items | 23.2 |
| 7h ago | okno tool items | 17.4 |
Read next
Its closest rival in Claude Code — same window, same units, with the leader marked on every row.
The pin next to it in Codex. 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, on test kit v6. Our measurements, not the vendor’s.