default

afi / afi · cli / proxy / Default profile / Qwen · qwen3 coder 30b a3b instruct high / afi 0.30.0

P50 across 0 scored trials

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

RecallNot recorded

Model-judged precisionNot recorded

Total billNot recorded

DurationNot recorded

Per-metric distributions

Exact Type-7 percentiles over complete scored samples; partial scored samples remain unavailable; non-scored trials are disclosed below

Recall 0/0 scored trials measured

Not recorded no scored trials for recall

Not recorded · 0 measured

Model-judged precision 0/0 scored trials measured

Not recorded no scored trials for precision

Not recorded · 0 measured

Total bill 0/0 scored trials measured

Not recorded no scored trials for total_bill

Not recorded · 0 measured

Duration 0/0 scored trials measured

Not recorded no scored trials for seconds

Not recorded · 0 measured

Metric	Availability	Measured	Min	P50	P95	Max
Findings `finding_count`	Not recorded no scored trials for finding_count	0/0	`-`	`-`	`-`	`-`
Defects found `found`	Not recorded no scored trials for found	0/0	`-`	`-`	`-`	`-`
Defects missed `missed`	Not recorded no scored trials for missed	0/0	`-`	`-`	`-`	`-`
Unkeyed findings `unkeyed`	Not recorded no scored trials for unkeyed	0/0	`-`	`-`	`-`	`-`
Intended findings `intended`	Not recorded no scored trials for intended	0/0	`-`	`-`	`-`	`-`
Recall `recall`	Not recorded no scored trials for recall	0/0	`-`	`-`	`-`	`-`
Model-judged precision `precision`	Not recorded no scored trials for precision	0/0	`-`	`-`	`-`	`-`
F1 `f1`	Not recorded no scored trials for f1	0/0	`-`	`-`	`-`	`-`
Tier 1 recall `tier_1`	Not recorded no scored trials for tier_1	0/0	`-`	`-`	`-`	`-`
Tier 2 recall `tier_2`	Not recorded no scored trials for tier_2	0/0	`-`	`-`	`-`	`-`
Tier 3 recall `tier_3`	Not recorded no scored trials for tier_3	0/0	`-`	`-`	`-`	`-`
Tier 4 recall `tier_4`	Not recorded no scored trials for tier_4	0/0	`-`	`-`	`-`	`-`
Security recall `category_security`	Not recorded no scored trials for category_security	0/0	`-`	`-`	`-`	`-`
Defect recall `category_defect`	Not recorded no scored trials for category_defect	0/0	`-`	`-`	`-`	`-`
Maintainability recall `category_maintainability`	Not recorded no scored trials for category_maintainability	0/0	`-`	`-`	`-`	`-`
Performance recall `category_performance`	Not recorded no scored trials for category_performance	0/0	`-`	`-`	`-`	`-`
Median anchor distance `anchor_median`	Not recorded no scored trials for anchor_median	0/0	`-`	`-`	`-`	`-`
Worst anchor distance `anchor_max`	Not recorded no scored trials for anchor_max	0/0	`-`	`-`	`-`	`-`
Refusals a judge overturned `anchor_missed`	Not recorded no scored trials for anchor_missed	0/0	`-`	`-`	`-`	`-`
Review bill `review_bill`	Not recorded no scored trials for review_bill	0/0	`-`	`-`	`-`	`-`
Judge bill `judge_bill`	Not recorded no scored trials for judge_bill	0/0	`-`	`-`	`-`	`-`
Total bill `total_bill`	Not recorded no scored trials for total_bill	0/0	`-`	`-`	`-`	`-`
Tokens `tokens`	Not recorded no scored trials for tokens	0/0	`-`	`-`	`-`	`-`
Duration `seconds`	Not recorded no scored trials for seconds	0/0	`-`	`-`	`-`	`-`
Carried findings `carried`	Not recorded no scored trials for carried	0/0	`-`	`-`	`-`	`-`

Compatibility identity

Any change to these inputs creates another group

Reviewer: afi
Reviewer tool: afi · cli
Subject: proxy
Reviewed SHA: 9b51f95ef609a219e211e37b082cd2e6913190e0
Key fingerprint: 000000000000
Settings fingerprint: 22ed7d19278f
Configuration ID: config-e857e321dd194f96
Build: afi 0.30.0 / b0f313c0b59a66ecc7612396dc8db0ea5da13a7a
Harness: bench 1 / 10b3b2068100b7ba429855e062500eaf83b90120 dirty
Adapter: afi 1 / sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c
Build ID: build-4ceb7cbd44e9619b
Cohort ID: cohort-d3b0aa35ac5bab82
Comparison ID: comparison-8be3c332d33c58a4

Comparison diagnostics

3 data-quality warnings remain attached to this compatible group

comparison-non-scored-trial

unscored trial excluded from aggregate metrics

afi/qwen3-coder-30b/20260831T111207Z

comparison-non-scored-trial

unscored trial excluded from aggregate metrics

afi/qwen3-coder-30b/20260831T111208Z

comparison-non-scored-trial

unscored trial excluded from aggregate metrics

afi/qwen3-coder-30b/20260831T111209Z

Trials

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

								Details
afi afi · cli	default Default profile · Qwen · qwen3 coder 30b a3b instruct high	proxy	31 Aug 2026, 11:17	N/A	N/A	Not recorded	unscored	View evidence
afi afi · cli	default Default profile · Qwen · qwen3 coder 30b a3b instruct high	proxy	31 Aug 2026, 11:16	N/A	N/A	Not recorded	unscored	View evidence
afi afi · cli	default Default profile · Qwen · qwen3 coder 30b a3b instruct high	proxy	31 Aug 2026, 11:16	N/A	N/A	Not recorded	unscored	View evidence

benchee benchee-dashboard-1