Integrity

Coverage

  • 603 logical evidence files
  • 54 compatible groups
  • 30 problems

Subject readiness, tier recall, and exporter problems; missing values never become zero

Answer-key coverage

Every run-referenced subject remains visible, including subjects with no scored trial

SubjectTier countsDefectsRunsAction
feat(proxy): reclaim space from the blob storeT1 3 / T2 7 / T3 6 / T4 42074Inspect subject

Tier recall matrix

Each row is one cohort, reviewer, configuration, and build; values are exporter medians within that row

Recall by discovery tier Higher recall uses a stronger tint; exact values and unavailable states remain visible
Subject / compatible group
Tier 1
Tier 2
Tier 3
Tier 4
proxy default
Reviewer afi · Tool afi · cli · Build afi 0.30.0 · 3 scored / 3 recorded
100%
42.9%
50%
50%
proxy default
Reviewer afi · Tool afi · cli · Build afi 0.30.0 · 2 scored / 2 recorded
66.7%
35.7%
50%
25%
proxy default
Reviewer afi · Tool afi · cli · Build afi 0.30.0 · 1 scored / 1 recorded
0%
28.6%
33.3%
0%
proxy default
Reviewer afi · Tool afi · cli · Build afi 0.30.0 · 0 scored / 3 recorded
Not recorded
Not recorded
Not recorded
Not recorded
proxy default
Reviewer afi · Tool afi · cli · Build afi 0.30.0 · 1 scored / 1 recorded
33.3%
42.9%
50%
25%
proxy default
Reviewer afi · Tool afi · cli · Build afi 0.30.0 · 0 scored / 1 recorded
Not recorded
Not recorded
Not recorded
Not recorded
proxy default
Reviewer afi · Tool afi · cli · Build afi 0.30.0 · 1 scored / 1 recorded
33.3%
0%
16.7%
25%
proxy default
Reviewer afi · Tool afi · cli · Build afi 0.30.0 · 1 scored / 1 recorded
33.3%
28.6%
33.3%
25%
proxy default
Reviewer afi · Tool afi · cli · Build afi 0.30.0 · 1 scored / 1 recorded
0%
0%
0%
0%
proxy default
Reviewer afi · Tool afi · cli · Build afi 0.30.0 · 1 scored / 1 recorded
33.3%
57.1%
33.3%
25%
proxy default
Reviewer afi · Tool afi · cli · Build afi 0.30.0 · 1 scored / 1 recorded
66.7%
57.1%
66.7%
50%
proxy default
Reviewer afi · Tool afi · cli · Build afi 0.30.0 · 1 scored / 1 recorded
66.7%
28.6%
50%
25%
ReviewerSubjectConfigurationBuildScored / recordedTier 1Tier 2Tier 3Tier 4
afi
afi · cli
proxydefault Default profile · OpenAI · gpt 5.6 sol highafi 0.30.03/3100%42.9%50%50%
afi
afi · cli
proxydefault Default profile · xAI · grok 4.5 highafi 0.30.02/266.7%35.7%50%25%
afi
afi · cli
proxydefault Default profile · Z.AI · glm 5.2 highafi 0.30.01/10%28.6%33.3%0%
afi
afi · cli
proxydefault Default profile · Meta · llama 4 maverick highafi 0.30.00/3Not recordedNot recordedNot recordedNot recorded
afi
afi · cli
proxydefault Default profile · Z.AI · glm 5.3 flash highafi 0.30.01/133.3%42.9%50%25%
afi
afi · cli
proxydefault Default profile · Mistral AI · devstral 2512 highafi 0.30.00/1Not recordedNot recordedNot recordedNot recorded
afi
afi · cli
proxydefault Default profile · Minimax · m3 highafi 0.30.01/133.3%0%16.7%25%
afi
afi · cli
proxydefault Default profile · Moonshot AI · kimi k2.7 code highafi 0.30.01/133.3%28.6%33.3%25%
afi
afi · cli
proxydefault Default profile · DeepSeek · v4 flash highafi 0.30.01/10%0%0%0%
afi
afi · cli
proxydefault Default profile · Z.AI · glm 5.3 highafi 0.30.01/133.3%57.1%33.3%25%
afi
afi · cli
proxydefault Default profile · DeepSeek · v4 pro highafi 0.30.01/166.7%57.1%66.7%50%
afi
afi · cli
proxydefault Default profile · xAI · grok 4.5 highafi 0.30.01/166.7%28.6%50%25%
All 54 comparison groups

Data quality

Paid, malformed, and partial records remain visible · showing 30 of 30 across 5 pages

findings-unavailable-note

afi wrote no findings document

afi/devstral-2512/20260831T163155Z
findings-unavailable-note

afi wrote no findings document

afi/devstral-2512/20260831T163156Z
findings-unavailable-note

afi wrote no findings document

afi/devstral-2512/20260831T163157Z
findings-unavailable-note

afi wrote no findings document

afi/llama-4-maverick/20260831T163158Z
findings-unavailable-note

afi wrote no findings document

afi/llama-4-maverick/20260831T163159Z
findings-unavailable-note

afi wrote no findings document

afi/llama-4-maverick/20260831T163200Z
findings-unavailable-note

afi wrote no findings document

afi/opus-5/20260831T152641Z
findings-unavailable-note

afi wrote no findings document

afi/opus-5/20260831T154400Z
findings-unavailable-note

afi wrote no findings document

afi/qwen3-coder-30b/20260831T111207Z
findings-unavailable-note

afi wrote no findings document

afi/qwen3-coder-30b/20260831T111208Z
findings-unavailable-note

afi wrote no findings document

afi/qwen3-coder-30b/20260831T111209Z
findings-unavailable-note

afi wrote no findings document

afi/qwen3.7-flash/20260831T125923Z
findings-unavailable-note

afi wrote no findings document

afi/qwen3.7-flash/20260831T125924Z
findings-unavailable-note

afi wrote no findings document

afi/qwen3.7-flash/20260831T125925Z
comparison-non-scored-trial

unscored trial excluded from aggregate metrics

afi/llama-4-maverick/20260831T163158Z
comparison-non-scored-trial

unscored trial excluded from aggregate metrics

afi/llama-4-maverick/20260831T163159Z
comparison-non-scored-trial

unscored trial excluded from aggregate metrics

afi/llama-4-maverick/20260831T163200Z
comparison-non-scored-trial

unscored trial excluded from aggregate metrics

afi/devstral-2512/20260831T163155Z
comparison-non-scored-trial

unscored trial excluded from aggregate metrics

afi/devstral-2512/20260831T163156Z
comparison-non-scored-trial

unscored trial excluded from aggregate metrics

afi/devstral-2512/20260831T163157Z
comparison-non-scored-trial

unscored trial excluded from aggregate metrics

afi/opus-5/20260831T152641Z
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
comparison-non-scored-trial

unscored trial excluded from aggregate metrics

afi/qwen3.7-flash/20260831T125923Z
comparison-non-scored-trial

unscored trial excluded from aggregate metrics

afi/qwen3.7-flash/20260831T125924Z
comparison-non-scored-trial

unscored trial excluded from aggregate metrics

afi/qwen3.7-flash/20260831T125925Z
comparison-non-scored-trial

unscored trial excluded from aggregate metrics

afi/opus-5/20260831T154400Z
session-run-state-mismatch

session records 'failed', but the linked run lifecycle records 'completed'

afi/deepseek-v4-pro/20260831T111226Z
session-run-missing

planned run has no native record yet

afi/sonnet-5/20260831T144454Z
benchee benchee-dashboard-1 built from 10f4ec58 Static benchmark evidence ·