# Claude Code & Codex today: measured speed, thinking and accuracy

As of 2026-10-03 20:37 UTC. Measured every hour from one EU server on paid subscriptions; each agent is compared with its own last 7 days.

Claude Code (Claude Opus 5.5) generated 110.4 tokens/s over the last 24 hours vs 110.6 tokens/s in the 7 days before (±0%) — no significant change (p=0.823).
Codex CLI (GPT-6 Astra) generated 22.5 tokens/s over the last 24 hours vs 28.2 tokens/s in the 7 days before (−20%) — no significant change (p=0.13).

## Right now

### Claude Code · Claude Opus 5.5: no significant change in the last 24 hours

- Speed: 110.4 tokens/s (7 days before: 110.6, ±0%) — no significant change (p=0.823)
- Thinking: 1,041 tokens (1,037, ±0%) — no significant change (p=0.747)
- First token: 3.0 s (3.1 s) — no significant change (p=0.888)
- Last measured 2026-10-03 20:37 UTC; claude-cli 2.1.288 (Claude Code); effort high; Claude Max subscription
- Served model reported by the CLI: claude-opus-5-5

### Codex CLI · GPT-6 Astra: no significant change in the last 24 hours

- Speed: 22.5 tokens/s (7 days before: 28.2, −20%) — no significant change (p=0.13)
- Thinking: 414 tokens (402, +3%) — no significant change (p=0.66)
- First token: 3.1 s (3.4 s) — no significant change (p=0.916)
- Last measured 2026-10-03 20:37 UTC; codex 0.156.1; effort high; ChatGPT Pro subscription
- The CLI does not report which model answered.

## Accuracy on a hard question panel

- Claude Code (Claude Opus 5.5): 11/19 correct (58%) so far; the baseline is still being collected (day 1 of 10), so no verdict until 2026-10-13.
- Codex CLI (GPT-6 Astra): 8/19 correct (42%) so far; the baseline is still being collected (day 1 of 10), so no verdict until 2026-10-13.

The panel (78 questions) is livenerf's calibrated panel (https://github.com/ninjahawk/livenerf), reused unchanged; questions are not published.

## Daily medians (tokens/s, thinking tokens)

| UTC day | Claude Code tokens/s | thinking | Codex CLI tokens/s | thinking |
|---|---|---|---|---|
| 2026-10-03 | 110.0 | 1,045 | 22.5 | 414 |
| 2026-10-02 | 109.8 | 1,036 | 22.2 | 397 |
| 2026-10-01 | 112.2 | 1,067 | 28.5 | 412 |
| 2026-09-30 | 108.9 | 998 | 28.7 | 398 |

Data: [/api/coding-agents.json](https://llmlatency.dev/api/coding-agents.json) (JSON, CC BY 4.0). Want another agent measured? Request it at [/coding-agents](https://llmlatency.dev/coding-agents#more).