← Valnivo Switchboard

grok-claude-bridge · performance report

Agent speed on the Oracle VM

How fast the bridge and its agents answer after moving to a larger Oracle machine, next to the first measurements.

Measured: 14 Oct 2026 (earlier figures: 13 Oct)Machine: Oracle VM (arm64, 4 OCPU / 24 GB, shared with other services)Subscription logins only, no API keys

Summary

1.7 msWhat the bridge itself adds to a request (median of 30)
3.7 sClaude, a one-word reply, end to end
10–29 tok/sGrok on the VM, three direct runs: its speed varies a lot

The bridge is not a bottleneck: it adds about 2 ms. Claude answers a one-word prompt in 3.7 s and a 250-word reply in 12.7 s. Several Claude jobs at once overlap well, and Claude and Grok together do not slow each other. Grok's speed changes from run to run (10 to 29 tok/s when run directly), so the ~65 tok/s measured on 13 Oct was a good moment, not a constant. Codex is still over its usage limit.

Output speed (approx. tokens per second)

Scale 0 to 100 tok/s. The faded 13 Oct bars came from longer replies (a Claude file write and a 450-word Grok essay), which spread the fixed start-up cost over more tokens, so compare 14 Oct with 14 Oct.

Latency and concurrency (14 Oct)

TestResult
Bridge overhead (30 calls, no agent)1.7 ms median, 2.2 ms p95
Claude, one-word reply (3 runs)3.7 s median (3.7 to 3.8)
Grok, one-word reply (3 runs)7.1 s median (5.4 to 16.9)
3 Claude jobs at once8.5 s in total, CPU 54%
4 Claude jobs at once8.6 s in total, CPU 62%
Claude and Grok together6.7 s in total (3.9 s and 6.7 s)

Four jobs at once cost no more than three, and memory stayed at about 22 GB free throughout.

Grok head to head

RunReplyTimeWordsSpeed
13 Oct · VM 1.0.52, direct400-word essay15.8 s456~65 tok/s
13 Oct · Mac 1.0.50, direct400-word essay22.3 s409~35 tok/s
14 Oct · VM 1.0.52, direct, run 1400-word essay22.6 s476~28 tok/s
14 Oct · VM 1.0.52, direct, run 2400-word essay53.9 s422~10 tok/s
14 Oct · VM 1.0.52, direct, run 3400-word essay18.4 s404~29 tok/s
14 Oct · VM 1.0.52, via bridge250-word essay75.6 s255~5 tok/s

The slow Grok runs are the provider's variance, not the machine or the bridge: the VM reaches the Grok service in a few tens of milliseconds, and the same CLI ran from 18 s to 54 s for the same prompt.

Status per agent

AgentVersionStateNotes
Claude Code2.1.299OK3.7 s for a one-word reply, 12.7 s for a 250-word reply; several jobs at once overlap.
Grok Build1.0.52VariableWorks, but its speed varies a lot from run to run; benchmark it several times before drawing conclusions.
Codex0.162.1LimitedUsage limit still hit; the quota fallback hands its jobs to Claude. Its sandbox works on the new VM (verified).

Method

What changed

Static report: the numbers are recorded by hand from the 14 Oct 2026 measurements and are not live. Nothing on this page reads from the bridges.