Run started 2026-10-18 11:13 UTC
· completed 11:27 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
73.23s
p50
62.18s
p90
114.18s
p99
121.03s
min
35.72s
max
121.79s
std
33.52s
First Insight Time
Time to the agent's first update, such as a tool call or a reasoning step.
mean
9.19s
p50
7.01s
p90
15.81s
p99
21.41s
min
4.68s
max
22.03s
std
6.65s
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
86.09s
p50
86.42s
p90
132.90s
p99
139.41s
min
0.01s
max
140.13s
std
44.67s
LLM Time
Total time inside LLM spans, summed across every LLM call in the case.
mean
47.73s
p50
45.52s
p90
62.78s
p99
62.84s
min
28.81s
max
62.85s
std
13.18s
Tool Time
Total time executing tools — database queries, API calls and the like.
mean
32.58s
p50
27.32s
p90
60.75s
p99
64.30s
min
9.42s
max
64.69s
std
24.05s
Other Time
Agent time outside the LLM and tools: orchestration overhead.
mean
0.00s
p50
0.00s
p90
0.00s
p99
0.00s
min
0.00s
max
0.00s
std
0.00s
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
68.6%
p50
69.7%
p90
81.8%
p99
83.7%
min
50.2%
max
84.0%
std
12.9%
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
39.4%
p50
40.0%
p90
55.9%
p99
58.8%
min
18.7%
max
59.1%
std
17.0%
Tool Calls
Number of tool spans the agent produced for the case.
mean
11.50
p50
12.00
p90
13.00
p99
13.00
min
8.00
max
13.00
std
1.87
sum
69.00
Total Tokens
LLM tokens consumed across every call in the case (prompt plus completion).