default

afi / afi · cli / proxy / Default profile / Moonshot AI · kimi k3 high / afi 0.30.0

Observed values from 1 scored trial

1 recorded; malformed and unscored trials remain inspectable but do not participate in aggregate metrics

Recall40%

Model-judged precisionN/A

Total bill$0.3550

Duration2m 45s

Per-metric observations

Exact values from the one complete scored sample; unavailable metrics and non-scored trials remain explicit

Recall 1/1 scored trials measured

Observed 40% One complete scored trial

Model-judged precision 0/1 scored trials measured

N/A no qualified judge decided these findings, so only locality was measured

N/A · 0 measured

Total bill 1/1 scored trials measured

Observed $0.3550 One complete scored trial

Duration 1/1 scored trials measured

Observed 2m 45s One complete scored trial

Metric	Availability	Measured	Min	P50	P95	Max
Findings `finding_count`	Measured	1/1	`8`	`8`	`8`	`8`
Defects found `found`	Measured	1/1	`8`	`8`	`8`	`8`
Defects missed `missed`	Measured	1/1	`12`	`12`	`12`	`12`
Unkeyed findings `unkeyed`	Measured	1/1	`0`	`0`	`0`	`0`
Intended findings `intended`	Measured	1/1	`0`	`0`	`0`	`0`
Recall `recall`	Measured	1/1	`40%`	`40%`	`40%`	`40%`
Model-judged precision `precision`	N/A no qualified judge decided these findings, so only locality was measured	0/1	`-`	`-`	`-`	`-`
F1 `f1`	N/A no qualified judge decided these findings, so only locality was measured	0/1	`-`	`-`	`-`	`-`
Tier 1 recall `tier_1`	Measured	1/1	`33.3%`	`33.3%`	`33.3%`	`33.3%`
Tier 2 recall `tier_2`	Measured	1/1	`28.6%`	`28.6%`	`28.6%`	`28.6%`
Tier 3 recall `tier_3`	Measured	1/1	`50%`	`50%`	`50%`	`50%`
Tier 4 recall `tier_4`	Measured	1/1	`50%`	`50%`	`50%`	`50%`
Security recall `category_security`	Measured	1/1	`0%`	`0%`	`0%`	`0%`
Defect recall `category_defect`	Measured	1/1	`46.2%`	`46.2%`	`46.2%`	`46.2%`
Maintainability recall `category_maintainability`	Measured	1/1	`0%`	`0%`	`0%`	`0%`
Performance recall `category_performance`	Measured	1/1	`66.7%`	`66.7%`	`66.7%`	`66.7%`
Median anchor distance `anchor_median`	Measured	1/1	`0`	`0`	`0`	`0`
Worst anchor distance `anchor_max`	Measured	1/1	`3`	`3`	`3`	`3`
Refusals a judge overturned `anchor_missed`	Not recorded no judging pass has looked beyond the scored slack	0/1	`-`	`-`	`-`	`-`
Review bill `review_bill`	Measured	1/1	`$0.3550`	`$0.3550`	`$0.3550`	`$0.3550`
Judge bill `judge_bill`	N/A no qualified judge decided these findings, so only locality was measured	0/1	`-`	`-`	`-`	`-`
Total bill `total_bill`	Measured	1/1	`$0.3550`	`$0.3550`	`$0.3550`	`$0.3550`
Tokens `tokens`	Measured	1/1	`41692`	`41692`	`41692`	`41692`
Duration `seconds`	Measured	1/1	`2m 45s`	`2m 45s`	`2m 45s`	`2m 45s`
Carried findings `carried`	Not recorded the reviewer reported no reuse figure	0/1	`-`	`-`	`-`	`-`

Compatibility identity

Any change to these inputs creates another group

Reviewer: afi
Reviewer tool: afi · cli
Subject: proxy
Reviewed SHA: 9b51f95ef609a219e211e37b082cd2e6913190e0
Key fingerprint: bd331c0b144e
Settings fingerprint: bcdf242be4e8
Configuration ID: config-9a0d29758e9a0aff
Build: afi 0.30.0 / b0f313c0b59a66ecc7612396dc8db0ea5da13a7a
Harness: bench 1 / 348a7e367b8c52f1ce72828ed09c15b0e9fac38b dirty
Adapter: afi 1 / sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c
Build ID: build-13a6e5be87bc4a53
Cohort ID: cohort-fdab2adfb8a4bd39
Comparison ID: comparison-908a56c0f29bc097

Trials

Select View evidence to inspect one run; the static table is paginated at 100 trials

								Details
afi afi · cli	default Default profile · Moonshot AI · kimi k3 high	proxy	31 Aug 2026, 16:13	40%	N/A	8	scored	View evidence

benchee benchee-dashboard-1