← Benchmarks

Benchmark #1 · smoke

done

1 scenarios × 1 · started Oct 27, 07:12 PM

Pass rate
100%
1 of 1 runs
Train
100%
1 of 1
Held-out
—
0 of 0
Time per run
41s
average, all turns
Tokens per run
18
estimated from the text

By scenario

ScenarioPass rateTimeTokens
A private fact, answered on Cohere
train · 1/1
100%
41s18

Each run is also an attempt under the agent benchmark:smoke, so it shows on the dashboard and in Attempts. Checks are patterns, not judgement: open a failed attempt to read Arkher's answer.