cc-os/plugins/os-context/eval/results/2026-07-06-baseline-grid.tsv

40 lines
2.2 KiB
Plaintext

E1N-pipeline-review haiku 1 PASS B:pass-mechanical tiers=sonnet=3;spawns=3
E1N-pipeline-review haiku 2 PASS B:pass-mechanical tiers=sonnet=2;spawns=2
E1N-pipeline-review haiku 3 PASS B:pass-judge tiers=sonnet=3;spawns=3
E1N-pipeline-review sonnet 1 PASS B:pass-mechanical tiers=;spawns=0
E1N-pipeline-review sonnet 2 PASS B:pass-mechanical tiers=;spawns=0
E1N-pipeline-review sonnet 3 PASS B:pass-mechanical tiers=;spawns=0
E1P-pipeline-review haiku 1 FAIL A:no-delegation
E1P-pipeline-review haiku 2 FAIL A:no-delegation
E1P-pipeline-review haiku 3 FAIL A:no-delegation
E1P-pipeline-review sonnet 1 FAIL A:no-delegation
E1P-pipeline-review sonnet 2 PASS A:pass;B:pass-mechanical tiers=sonnet=6;mismatched=6
E1P-pipeline-review sonnet 3 FAIL A:no-delegation
E2N-readme-typo haiku 1 PASS A:no-spawn pre_bytes=1201
E2N-readme-typo haiku 2 PASS A:no-spawn pre_bytes=1201
E2N-readme-typo haiku 3 PASS A:no-spawn pre_bytes=1201
E2N-readme-typo sonnet 1 PASS A:no-spawn pre_bytes=483
E2N-readme-typo sonnet 2 PASS A:no-spawn pre_bytes=334
E2N-readme-typo sonnet 3 PASS A:no-spawn pre_bytes=398
E2P-retry-policy haiku 1 FAIL A:no-delegation
E2P-retry-policy haiku 2 FAIL A:no-delegation
E2P-retry-policy haiku 3 FAIL A:no-delegation
E2P-retry-policy sonnet 1 FAIL A:no-delegation
E2P-retry-policy sonnet 2 FAIL A:no-delegation
E2P-retry-policy sonnet 3 FAIL A:no-delegation
E3N-brand-spelling haiku 1 PASS A:no-spawn pre_bytes=2983;edited=yes
E3N-brand-spelling haiku 2 PASS A:no-spawn pre_bytes=2990;edited=yes
E3N-brand-spelling haiku 3 PASS A:no-spawn pre_bytes=2927;edited=yes
E3N-brand-spelling sonnet 1 PASS A:no-spawn pre_bytes=1967;edited=yes
E3N-brand-spelling sonnet 2 PASS A:no-spawn pre_bytes=790;edited=yes
E3N-brand-spelling sonnet 3 PASS A:no-spawn pre_bytes=1550;edited=yes
E3P-dropped-events haiku 1 FAIL A:no-delegation
E3P-dropped-events haiku 2 FAIL A:no-delegation
E3P-dropped-events haiku 3 FAIL A:no-delegation
E3P-dropped-events sonnet 1 FAIL A:no-delegation
E3P-dropped-events sonnet 2 FAIL A:no-delegation
E3P-dropped-events sonnet 3 FAIL A:no-delegation
# canary reps (counted; wording v1 then v2):
E1P-pipeline-review sonnet 1 FAIL A:pass;B:fail-mechanical tiers=sonnet=3;mismatched=3
E1P-pipeline-review sonnet 1 FAIL A:no-delegation