Run started 2026-10-18 07:09 UTC
· completed 07:17 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
92.38s
p50
86.48s
p90
130.81s
p99
131.69s
min
53.86s
max
131.72s
std
28.33s
First Insight Time
Time to the agent's first update, such as a tool call or a reasoning step.
mean
8.53s
p50
9.09s
p90
10.76s
p99
14.28s
min
3.92s
max
14.70s
std
2.91s
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
90.63s
p50
93.60s
p90
138.03s
p99
140.58s
min
10.94s
max
140.92s
std
43.44s
LLM Time
Total time inside LLM spans, summed across every LLM call in the case.
mean
63.73s
p50
57.06s
p90
100.59s
p99
110.06s
min
34.56s
max
111.01s
std
23.67s
Tool Time
Total time executing tools — database queries, API calls and the like.
mean
31.33s
p50
27.88s
p90
51.40s
p99
70.44s
min
6.50s
max
72.73s
std
19.80s
Other Time
Agent time outside the LLM and tools: orchestration overhead.
mean
2.06s
p50
1.63s
p90
3.69s
p99
7.42s
min
0.00s
max
7.88s
std
2.32s
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
67.0%
p50
68.8%
p90
85.3%
p99
88.2%
min
39.5%
max
88.5%
std
16.4%
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
32.0%
p50
29.0%
p90
52.1%
p99
56.8%
min
9.9%
max
57.3%
std
16.8%
Tool Calls
Number of tool spans the agent produced for the case.
mean
11.25
p50
10.50
p90
15.80
p99
16.89
min
8.00
max
17.00
std
3.17
sum
135.00
Total Tokens
LLM tokens consumed across every call in the case (prompt plus completion).