Run started 2026-10-19 08:11 UTC
· completed 08:20 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
151.30s
p50
151.30s
p90
151.30s
p99
151.30s
min
151.30s
max
151.30s
std
0.00s
First Insight Time
Time to the agent's first update, such as a tool call or a reasoning step.
mean
4.08s
p50
4.08s
p90
4.08s
p99
4.08s
min
4.08s
max
4.08s
std
0.00s
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
193.65s
p50
193.65s
p90
193.65s
p99
193.65s
min
193.65s
max
193.65s
std
0.00s
LLM Time
Total time inside LLM spans, summed across every LLM call in the case.
mean
99.23s
p50
99.23s
p90
99.23s
p99
99.23s
min
99.23s
max
99.23s
std
0.00s
Tool Time
Total time executing tools — database queries, API calls and the like.
mean
59.39s
p50
59.39s
p90
59.39s
p99
59.39s
min
59.39s
max
59.39s
std
0.00s
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
65.4%
p50
65.4%
p90
65.4%
p99
65.4%
min
65.4%
max
65.4%
std
0.0%
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
39.2%
p50
39.2%
p90
39.2%
p99
39.2%
min
39.2%
max
39.2%
std
0.0%
Tool Calls
Number of tool spans the agent produced for the case.
mean
20.00
p50
20.00
p90
20.00
p99
20.00
min
20.00
max
20.00
std
0.00
sum
20.00
Total Tokens
LLM tokens consumed across every call in the case (prompt plus completion).