Remove benchmark skill

This commit is contained in:
2026-07-31 18:50:42 -04:00
parent 8479ad096c
commit d3bc9a5760
11 changed files with 4 additions and 4184 deletions

View File

@@ -1,496 +0,0 @@
{
"skill": "clean-skill",
"generatedAt": "2026-07-24T10:00:00Z",
"temperature": 1.0,
"trialsPerCase": 5,
"arms": [
{
"id": "new",
"label": "New skill"
},
{
"id": "previous",
"label": "Previous version"
},
{
"id": "baseline",
"label": "No skill"
}
],
"comparisons": [
{
"id": "efficacy",
"label": "Efficacy",
"new": "new",
"against": "baseline",
"rule": "efficacy"
},
{
"id": "regression",
"label": "Regression",
"new": "new",
"against": "previous",
"rule": "regression"
}
],
"cases": [
{
"name": "narrowest",
"description": "narrowest scenario",
"softCriteria": [
"a good answer for narrowest"
],
"trials": [
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-narrowest-t0",
"previous": "OUT-previous-narrowest-t0",
"baseline": "OUT-baseline-narrowest-t0"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-narrowest-t1",
"previous": "OUT-previous-narrowest-t1",
"baseline": "OUT-baseline-narrowest-t1"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-narrowest-t2",
"previous": "OUT-previous-narrowest-t2",
"baseline": "OUT-baseline-narrowest-t2"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "tie",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-narrowest-t3",
"previous": "OUT-previous-narrowest-t3",
"baseline": "OUT-baseline-narrowest-t3"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "tie",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-narrowest-t4",
"previous": "OUT-previous-narrowest-t4",
"baseline": "OUT-baseline-narrowest-t4"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
}
]
},
{
"name": "roomy",
"description": "roomy scenario",
"softCriteria": [
"a good answer for roomy"
],
"trials": [
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "new",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-roomy-t0",
"previous": "OUT-previous-roomy-t0",
"baseline": "OUT-baseline-roomy-t0"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-roomy-t1",
"previous": "OUT-previous-roomy-t1",
"baseline": "OUT-baseline-roomy-t1"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-roomy-t2",
"previous": "OUT-previous-roomy-t2",
"baseline": "OUT-baseline-roomy-t2"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-roomy-t3",
"previous": "OUT-previous-roomy-t3",
"baseline": "OUT-baseline-roomy-t3"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-roomy-t4",
"previous": "OUT-previous-roomy-t4",
"baseline": "OUT-baseline-roomy-t4"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
}
]
}
]
}

View File

@@ -1,725 +0,0 @@
{
"skill": "fragile-skill",
"generatedAt": "2026-07-24T11:00:00Z",
"temperature": 1.0,
"trialsPerCase": 5,
"arms": [
{
"id": "new",
"label": "New skill"
},
{
"id": "previous",
"label": "Previous version"
},
{
"id": "baseline",
"label": "No skill"
}
],
"comparisons": [
{
"id": "efficacy",
"label": "Efficacy",
"new": "new",
"against": "baseline",
"rule": "efficacy"
},
{
"id": "regression",
"label": "Regression",
"new": "new",
"against": "previous",
"rule": "regression"
}
],
"cases": [
{
"name": "both",
"description": "both scenario",
"softCriteria": [
"a good answer for both"
],
"trials": [
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "new",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-both-t0",
"previous": "OUT-previous-both-t0",
"baseline": "OUT-baseline-both-t0"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-both-t1",
"previous": "OUT-previous-both-t1",
"baseline": "OUT-baseline-both-t1"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-both-t2",
"previous": "OUT-previous-both-t2",
"baseline": "OUT-baseline-both-t2"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "tie",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-both-t3",
"previous": "OUT-previous-both-t3",
"baseline": "OUT-baseline-both-t3"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "tie",
"rationale": "fixture"
},
"regression": {
"winner": "previous",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-both-t4",
"previous": "OUT-previous-both-t4",
"baseline": "OUT-baseline-both-t4"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
}
]
},
{
"name": "reg-only",
"description": "reg-only scenario",
"softCriteria": [
"a good answer for reg-only"
],
"trials": [
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-reg-only-t0",
"previous": "OUT-previous-reg-only-t0",
"baseline": "OUT-baseline-reg-only-t0"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-reg-only-t1",
"previous": "OUT-previous-reg-only-t1",
"baseline": "OUT-baseline-reg-only-t1"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-reg-only-t2",
"previous": "OUT-previous-reg-only-t2",
"baseline": "OUT-baseline-reg-only-t2"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-reg-only-t3",
"previous": "OUT-previous-reg-only-t3",
"baseline": "OUT-baseline-reg-only-t3"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "previous",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-reg-only-t4",
"previous": "OUT-previous-reg-only-t4",
"baseline": "OUT-baseline-reg-only-t4"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
}
]
},
{
"name": "none",
"description": "none scenario",
"softCriteria": [
"a good answer for none"
],
"trials": [
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-none-t0",
"previous": "OUT-previous-none-t0",
"baseline": "OUT-baseline-none-t0"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-none-t1",
"previous": "OUT-previous-none-t1",
"baseline": "OUT-baseline-none-t1"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-none-t2",
"previous": "OUT-previous-none-t2",
"baseline": "OUT-baseline-none-t2"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-none-t3",
"previous": "OUT-previous-none-t3",
"baseline": "OUT-baseline-none-t3"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
},
{
"hard": {
"ran": true,
"pass": true
},
"comparisons": {
"efficacy": {
"winner": "tie",
"rationale": "fixture"
},
"regression": {
"winner": "tie",
"rationale": "fixture"
}
},
"outputs": {
"new": "OUT-new-none-t4",
"previous": "OUT-previous-none-t4",
"baseline": "OUT-baseline-none-t4"
},
"usage": {
"new": {
"input": 1000,
"output": 500,
"cacheCreation": 200,
"cacheRead": 300,
"turns": 3
},
"previous": {
"input": 900,
"output": 450,
"cacheCreation": 180,
"cacheRead": 270,
"turns": 3
},
"baseline": {
"input": 600,
"output": 300,
"cacheCreation": 0,
"cacheRead": 0,
"turns": 2
}
}
}
]
}
]
}

View File

@@ -1,954 +0,0 @@
{
"skill": "sample-skill",
"generatedAt": "2026-07-24T12:00:00Z",
"temperature": 1.0,
"trialsPerCase": 5,
"arms": [
{
"id": "new",
"label": "New skill"
},
{
"id": "previous",
"label": "Previous version"
},
{
"id": "baseline",
"label": "No skill"
}
],
"comparisons": [
{
"id": "efficacy",
"label": "Efficacy",
"new": "new",
"against": "baseline",
"rule": "efficacy"
},
{
"id": "regression",
"label": "Regression",
"new": "new",
"against": "previous",
"rule": "regression"
}
],
"cases": [
{
"name": "clean-both",
"description": "New beats baseline and holds steady versus the previous version.",
"softCriteria": [
"The answer is grounded in the fixture."
],
"trials": [
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
},
"regression": {
"winner": "tie",
"rationale": "judge: regression tie"
}
},
"outputs": {
"new": "OUT-new-clean-both-t0",
"previous": "OUT-previous-clean-both-t0",
"baseline": "OUT-baseline-clean-both-t0"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
},
"regression": {
"winner": "tie",
"rationale": "judge: regression tie"
}
},
"outputs": {
"new": "OUT-new-clean-both-t1",
"previous": "OUT-previous-clean-both-t1",
"baseline": "OUT-baseline-clean-both-t1"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
},
"regression": {
"winner": "new",
"rationale": "judge: regression new"
}
},
"outputs": {
"new": "OUT-new-clean-both-t2",
"previous": "OUT-previous-clean-both-t2",
"baseline": "OUT-baseline-clean-both-t2"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
},
"regression": {
"winner": "tie",
"rationale": "judge: regression tie"
}
},
"outputs": {
"new": "OUT-new-clean-both-t3",
"previous": "OUT-previous-clean-both-t3",
"baseline": "OUT-baseline-clean-both-t3"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "tie",
"rationale": "judge: efficacy tie"
},
"regression": {
"winner": "tie",
"rationale": "judge: regression tie"
}
},
"outputs": {
"new": "OUT-new-clean-both-t4",
"previous": "OUT-previous-clean-both-t4",
"baseline": "OUT-baseline-clean-both-t4"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
}
]
},
{
"name": "regressed-still-valuable",
"description": "New still beats baseline but has degraded from the previous version.",
"softCriteria": [
"The answer resolves the user's request."
],
"trials": [
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
},
"regression": {
"winner": "previous",
"rationale": "judge: regression previous"
}
},
"outputs": {
"new": "OUT-new-regressed-still-valuable-t0",
"previous": "OUT-previous-regressed-still-valuable-t0",
"baseline": "OUT-baseline-regressed-still-valuable-t0"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
},
"regression": {
"winner": "previous",
"rationale": "judge: regression previous"
}
},
"outputs": {
"new": "OUT-new-regressed-still-valuable-t1",
"previous": "OUT-previous-regressed-still-valuable-t1",
"baseline": "OUT-baseline-regressed-still-valuable-t1"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
},
"regression": {
"winner": "tie",
"rationale": "judge: regression tie"
}
},
"outputs": {
"new": "OUT-new-regressed-still-valuable-t2",
"previous": "OUT-previous-regressed-still-valuable-t2",
"baseline": "OUT-baseline-regressed-still-valuable-t2"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "tie",
"rationale": "judge: efficacy tie"
},
"regression": {
"winner": "new",
"rationale": "judge: regression new"
}
},
"outputs": {
"new": "OUT-new-regressed-still-valuable-t3",
"previous": "OUT-previous-regressed-still-valuable-t3",
"baseline": "OUT-baseline-regressed-still-valuable-t3"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
},
"regression": {
"winner": "tie",
"rationale": "judge: regression tie"
}
},
"outputs": {
"new": "OUT-new-regressed-still-valuable-t4",
"previous": "OUT-previous-regressed-still-valuable-t4",
"baseline": "OUT-baseline-regressed-still-valuable-t4"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
}
]
},
{
"name": "dead-weight",
"description": "New does not beat baseline, but the edit did not make it worse.",
"softCriteria": [
"The answer is correct."
],
"trials": [
{
"comparisons": {
"efficacy": {
"winner": "tie",
"rationale": "judge: efficacy tie"
},
"regression": {
"winner": "new",
"rationale": "judge: regression new"
}
},
"outputs": {
"new": "OUT-new-dead-weight-t0",
"previous": "OUT-previous-dead-weight-t0",
"baseline": "OUT-baseline-dead-weight-t0"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "tie",
"rationale": "judge: efficacy tie"
},
"regression": {
"winner": "new",
"rationale": "judge: regression new"
}
},
"outputs": {
"new": "OUT-new-dead-weight-t1",
"previous": "OUT-previous-dead-weight-t1",
"baseline": "OUT-baseline-dead-weight-t1"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "baseline",
"rationale": "judge: efficacy baseline"
},
"regression": {
"winner": "tie",
"rationale": "judge: regression tie"
}
},
"outputs": {
"new": "OUT-new-dead-weight-t2",
"previous": "OUT-previous-dead-weight-t2",
"baseline": "OUT-baseline-dead-weight-t2"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "tie",
"rationale": "judge: efficacy tie"
},
"regression": {
"winner": "new",
"rationale": "judge: regression new"
}
},
"outputs": {
"new": "OUT-new-dead-weight-t3",
"previous": "OUT-previous-dead-weight-t3",
"baseline": "OUT-baseline-dead-weight-t3"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "tie",
"rationale": "judge: efficacy tie"
},
"regression": {
"winner": "tie",
"rationale": "judge: regression tie"
}
},
"outputs": {
"new": "OUT-new-dead-weight-t4",
"previous": "OUT-previous-dead-weight-t4",
"baseline": "OUT-baseline-dead-weight-t4"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
}
]
},
{
"name": "hard-gate-fail",
"description": "New sweeps both head-to-heads but violates a hard assertion.",
"softCriteria": [
"The output is well-formed."
],
"trials": [
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
},
"regression": {
"winner": "tie",
"rationale": "judge: regression tie"
}
},
"outputs": {
"new": "OUT-new-hard-gate-fail-t0",
"previous": "OUT-previous-hard-gate-fail-t0",
"baseline": "OUT-baseline-hard-gate-fail-t0"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
},
"regression": {
"winner": "tie",
"rationale": "judge: regression tie"
}
},
"outputs": {
"new": "OUT-new-hard-gate-fail-t1",
"previous": "OUT-previous-hard-gate-fail-t1",
"baseline": "OUT-baseline-hard-gate-fail-t1"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
},
"regression": {
"winner": "tie",
"rationale": "judge: regression tie"
}
},
"outputs": {
"new": "OUT-new-hard-gate-fail-t2",
"previous": "OUT-previous-hard-gate-fail-t2",
"baseline": "OUT-baseline-hard-gate-fail-t2"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": false
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
},
"regression": {
"winner": "tie",
"rationale": "judge: regression tie"
}
},
"outputs": {
"new": "OUT-new-hard-gate-fail-t3",
"previous": "OUT-previous-hard-gate-fail-t3",
"baseline": "OUT-baseline-hard-gate-fail-t3"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
},
"regression": {
"winner": "tie",
"rationale": "judge: regression tie"
}
},
"outputs": {
"new": "OUT-new-hard-gate-fail-t4",
"previous": "OUT-previous-hard-gate-fail-t4",
"baseline": "OUT-baseline-hard-gate-fail-t4"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
},
"previous": {
"input": 800,
"output": 1600,
"cacheCreation": 300,
"cacheRead": 6000,
"turns": 3
}
},
"hard": {
"ran": true,
"pass": true
}
}
]
}
]
}

View File

@@ -1,515 +0,0 @@
{
"skill": "sample-skill-2arm",
"generatedAt": "2026-07-24T12:00:00Z",
"temperature": 1.0,
"trialsPerCase": 5,
"arms": [
{
"id": "new",
"label": "New skill"
},
{
"id": "baseline",
"label": "No skill"
}
],
"comparisons": [
{
"id": "efficacy",
"label": "Efficacy",
"new": "new",
"against": "baseline",
"rule": "efficacy"
}
],
"cases": [
{
"name": "clean-pass",
"description": "New skill reliably beats the no-skill baseline.",
"softCriteria": [
"The answer is grounded in the fixture.",
"The answer follows the skill's format."
],
"trials": [
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
}
},
"outputs": {
"new": "OUT-new-clean-pass-t0",
"baseline": "OUT-baseline-clean-pass-t0"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
}
},
"outputs": {
"new": "OUT-new-clean-pass-t1",
"baseline": "OUT-baseline-clean-pass-t1"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
}
},
"outputs": {
"new": "OUT-new-clean-pass-t2",
"baseline": "OUT-baseline-clean-pass-t2"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
}
},
"outputs": {
"new": "OUT-new-clean-pass-t3",
"baseline": "OUT-baseline-clean-pass-t3"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "tie",
"rationale": "judge: efficacy tie"
}
},
"outputs": {
"new": "OUT-new-clean-pass-t4",
"baseline": "OUT-baseline-clean-pass-t4"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
}
},
"hard": {
"ran": true,
"pass": true
}
}
]
},
{
"name": "regresses-baseline",
"description": "New skill does not reliably beat the baseline.",
"softCriteria": [
"The answer resolves the user's request."
],
"trials": [
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
}
},
"outputs": {
"new": "OUT-new-regresses-baseline-t0",
"baseline": "OUT-baseline-regresses-baseline-t0"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
}
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
}
},
"outputs": {
"new": "OUT-new-regresses-baseline-t1",
"baseline": "OUT-baseline-regresses-baseline-t1"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
}
}
},
{
"comparisons": {
"efficacy": {
"winner": "tie",
"rationale": "judge: efficacy tie"
}
},
"outputs": {
"new": "OUT-new-regresses-baseline-t2",
"baseline": "OUT-baseline-regresses-baseline-t2"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
}
}
},
{
"comparisons": {
"efficacy": {
"winner": "baseline",
"rationale": "judge: efficacy baseline"
}
},
"outputs": {
"new": "OUT-new-regresses-baseline-t3",
"baseline": "OUT-baseline-regresses-baseline-t3"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
}
}
},
{
"comparisons": {
"efficacy": {
"winner": "baseline",
"rationale": "judge: efficacy baseline"
}
},
"outputs": {
"new": "OUT-new-regresses-baseline-t4",
"baseline": "OUT-baseline-regresses-baseline-t4"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
}
}
}
]
},
{
"name": "hard-gate-fail",
"description": "Output wins the head-to-head but violates a hard assertion.",
"softCriteria": [
"The output is correct."
],
"trials": [
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
}
},
"outputs": {
"new": "OUT-new-hard-gate-fail-t0",
"baseline": "OUT-baseline-hard-gate-fail-t0"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
}
},
"outputs": {
"new": "OUT-new-hard-gate-fail-t1",
"baseline": "OUT-baseline-hard-gate-fail-t1"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
}
},
"outputs": {
"new": "OUT-new-hard-gate-fail-t2",
"baseline": "OUT-baseline-hard-gate-fail-t2"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
}
},
"hard": {
"ran": true,
"pass": false
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
}
},
"outputs": {
"new": "OUT-new-hard-gate-fail-t3",
"baseline": "OUT-baseline-hard-gate-fail-t3"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
}
},
"hard": {
"ran": true,
"pass": true
}
},
{
"comparisons": {
"efficacy": {
"winner": "new",
"rationale": "judge: efficacy new"
}
},
"outputs": {
"new": "OUT-new-hard-gate-fail-t4",
"baseline": "OUT-baseline-hard-gate-fail-t4"
},
"usage": {
"new": {
"input": 1000,
"output": 2000,
"cacheCreation": 400,
"cacheRead": 8000,
"turns": 3
},
"baseline": {
"input": 500,
"output": 1000,
"cacheCreation": 200,
"cacheRead": 4000,
"turns": 2
}
},
"hard": {
"ran": true,
"pass": true
}
}
]
}
]
}