Run started 2026-10-19 00:14 UTC
· completed 00:55 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
82.34s
p50
76.92s
p90
145.95s
p99
208.05s
min
11.45s
max
237.16s
std
45.91s
First Insight Time
Time to the agent's first update, such as a tool call or a reasoning step.
mean
9.48s
p50
5.30s
p90
16.64s
p99
53.58s
min
2.84s
max
75.40s
std
11.50s
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
93.74s
p50
87.86s
p90
165.74s
p99
217.46s
min
23.30s
max
251.29s
std
48.05s
LLM Time
Total time inside LLM spans, summed across every LLM call in the case.
mean
56.53s
p50
45.78s
p90
105.92s
p99
164.74s
min
14.49s
max
197.50s
std
36.25s
Tool Time
Total time executing tools — database queries, API calls and the like.
mean
29.11s
p50
25.13s
p90
55.11s
p99
87.03s
min
0.27s
max
100.18s
std
20.17s
Other Time
Agent time outside the LLM and tools: orchestration overhead.
mean
0.95s
p50
0.00s
p90
2.26s
p99
15.02s
min
0.00s
max
25.40s
std
3.72s
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
67.8%
p50
67.8%
p90
87.8%
p99
106.8%
min
31.0%
max
112.9%
std
18.1%
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
34.4%
p50
33.7%
p90
56.6%
p99
79.4%
min
1.7%
max
81.2%
std
18.0%
Tool Calls
Number of tool spans the agent produced for the case.
mean
9.81
p50
10.00
p90
13.00
p99
16.06
min
2.00
max
17.00
std
2.94
sum
471.00
Total Tokens
LLM tokens consumed across every call in the case (prompt plus completion).