Run started 2026-10-17 09:22 UTC
· completed 09:27 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
92.00s
p50
85.00s
p90
128.34s
p99
143.43s
min
54.00s
max
145.11s
std
34.68s
First Insight Time
Time to the agent's first update, such as a tool call or a reasoning step.
mean
17.04s
p50
11.14s
p90
29.67s
p99
39.07s
min
8.93s
max
40.11s
std
13.03s
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
96.40s
p50
95.97s
p90
135.44s
p99
153.11s
min
20.71s
max
155.07s
std
38.10s
LLM Time
Total time inside LLM spans, summed across every LLM call in the case.
mean
67.58s
p50
68.62s
p90
100.64s
p99
116.43s
min
31.80s
max
118.18s
std
33.16s
Tool Time
Total time executing tools — database queries, API calls and the like.
mean
28.58s
p50
28.91s
p90
32.04s
p99
33.42s
min
23.67s
max
33.57s
std
3.64s
Other Time
Agent time outside the LLM and tools: orchestration overhead.
mean
0.95s
p50
0.34s
p90
2.41s
p99
3.13s
min
0.00s
max
3.21s
std
1.36s
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
68.0%
p50
68.1%
p90
77.9%
p99
79.5%
min
56.5%
max
79.6%
std
9.7%
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
33.3%
p50
30.8%
p90
47.3%
p99
52.3%
min
18.2%
max
52.8%
std
13.2%
Tool Calls
Number of tool spans the agent produced for the case.
mean
13.60
p50
14.00
p90
17.00
p99
17.00
min
7.00
max
17.00
std
4.10
sum
68.00
Total Tokens
LLM tokens consumed across every call in the case (prompt plus completion).