Run started 2026-10-19 08:37 UTC
· completed 08:40 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
48.85s
p50
48.85s
p90
48.85s
p99
48.85s
min
48.85s
max
48.85s
std
0.00s
First Insight Time
Time to the agent's first update, such as a tool call or a reasoning step.
mean
3.42s
p50
3.42s
p90
3.42s
p99
3.42s
min
3.42s
max
3.42s
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
78.69s
p50
78.69s
p90
78.69s
p99
78.69s
min
78.69s
max
78.69s
std
0.00s
LLM Time
Total time inside LLM spans, summed across every LLM call in the case.
mean
37.10s
p50
37.10s
p90
37.10s
p99
37.10s
min
37.10s
max
37.10s
std
0.00s
Tool Time
Total time executing tools — database queries, API calls and the like.
mean
12.80s
p50
12.80s
p90
12.80s
p99
12.80s
min
12.80s
max
12.80s
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
74.9%
p50
74.9%
p90
74.9%
p99
74.9%
min
74.9%
max
74.9%
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
25.9%
p50
25.9%
p90
25.9%
p99
25.9%
min
25.9%
max
25.9%
std
0.0%
Tool Calls
Number of tool spans the agent produced for the case.
mean
9.00
p50
9.00
p90
9.00
p99
9.00
min
9.00
max
9.00
std
0.00
sum
9.00
Total Tokens
LLM tokens consumed across every call in the case (prompt plus completion).