Run started 2026-10-19 05:44 UTC
· completed 05:54 UTC
Headline Metrics
A case passes when (Correctness or String in Response) and Relevance and Tools pass.
Scorers that had nothing to judge are ignored; cases where no scorer produced a result are
counted as no data and excluded from every pass rate.
First Token Time
Time to the first response token (TTFT) — how long before the user sees anything.
mean
82.89s
p50
85.54s
p90
102.87s
p99
107.95s
min
37.06s
max
108.51s
std
23.25s
First Insight Time
Time to the agent's first update, such as a tool call or a reasoning step.
mean
5.55s
p50
4.62s
p90
7.79s
p99
13.00s
min
2.99s
max
13.58s
std
3.32s
Case Duration
Wall-clock time the eval harness measured for the whole case, including scoring and gRPC overhead. Always at least the agent's own time_total.
mean
102.04s
p50
104.82s
p90
128.79s
p99
136.07s
min
63.42s
max
136.88s
std
24.60s
LLM Time
Total time inside LLM spans, summed across every LLM call in the case.
mean
55.20s
p50
58.33s
p90
73.55s
p99
75.38s
min
28.97s
max
75.58s
std
17.42s
Tool Time
Total time executing tools — database queries, API calls and the like.
mean
33.82s
p50
31.05s
p90
49.89s
p99
51.76s
min
15.35s
max
51.97s
std
12.72s
Other Time
Agent time outside the LLM and tools: orchestration overhead.
mean
0.10s
p50
0.00s
p90
0.24s
p99
0.75s
min
0.00s
max
0.81s
std
0.29s
LLM Time Share
LLM time as a percentage of the agent's total span duration. This is the spread of per-case percentages, not the run-level ratio.
mean
64.2%
p50
66.5%
p90
73.7%
p99
74.9%
min
41.4%
max
75.0%
std
11.3%
Tool Time Share
Tool time as a percentage of the agent's total span duration. This is the spread of per-case percentages, not the run-level ratio.
mean
39.8%
p50
35.7%
p90
53.8%
p99
67.7%
min
25.5%
max
69.2%
std
13.4%
Tool Calls
Number of tool spans the agent produced for the case.
mean
14.25
p50
14.00
p90
17.30
p99
17.93
min
11.00
max
18.00
std
2.38
sum
114.00
Total Tokens
LLM tokens consumed across every call in the case (prompt plus completion).