Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
88 changes: 72 additions & 16 deletions bench/baselines/quality/current.json
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"version": "1.3.0",
"gitRef": "0e7aab2fe3c65661d7735303b15a7010e280a649",
"generated": "2026-03-21T14:11:05.599Z",
"version": "1.4.0",
"gitRef": "b983bb4283b942c045c3ff01c93933625fb41ff2",
"generated": "2026-03-22T16:49:09.591Z",
"results": {
"scenarios": {
"Coding assistant": {
Expand Down Expand Up @@ -100,7 +100,8 @@
"entityRetention": 1,
"codeBlocksIntact": true
}
]
],
"overheadRatio": 0.0003203430451127824
},
"Long Q&A": {
"ratio": 4.902912621359223,
Expand Down Expand Up @@ -190,7 +191,8 @@
"entityRetention": 1,
"codeBlocksIntact": true
}
]
],
"overheadRatio": 0.00006223777662517271
},
"Tool-heavy": {
"ratio": 1.4009797060881735,
Expand Down Expand Up @@ -249,7 +251,8 @@
"entityRetention": 0.6,
"codeBlocksIntact": true
}
]
],
"overheadRatio": 0.00009947913793103351
},
"Deep conversation": {
"ratio": 2.5041568769202964,
Expand Down Expand Up @@ -752,7 +755,8 @@
"entityRetention": 1,
"codeBlocksIntact": true
}
]
],
"overheadRatio": 0.000041621278337531585
},
"Technical explanation": {
"ratio": 1.2398561890087314,
Expand Down Expand Up @@ -824,7 +828,8 @@
"entityRetention": 1,
"codeBlocksIntact": true
}
]
],
"overheadRatio": 0.000056277095375722494
},
"Structured content": {
"ratio": 1.2595769010863351,
Expand Down Expand Up @@ -879,7 +884,8 @@
"entityRetention": 0.6,
"codeBlocksIntact": true
}
]
],
"overheadRatio": 0.000031551811023622734
},
"Agentic coding session": {
"ratio": 1.004950495049505,
Expand Down Expand Up @@ -925,7 +931,8 @@
"entityRetention": 0.2857142857142857,
"codeBlocksIntact": true
}
]
],
"overheadRatio": 0.00012199074074074208
},
"Single-char messages": {
"ratio": 1,
Expand Down Expand Up @@ -953,7 +960,8 @@
],
"negativeCompressions": 0,
"coherenceIssues": 0,
"messages": []
"messages": [],
"overheadRatio": 0.00007007500000000277
},
"Giant single message": {
"ratio": 2.828036762263315,
Expand Down Expand Up @@ -999,7 +1007,8 @@
"entityRetention": 1,
"codeBlocksIntact": true
}
]
],
"overheadRatio": 0.00002075325774184707
},
"Code-only conversation": {
"ratio": 1,
Expand Down Expand Up @@ -1031,7 +1040,8 @@
],
"negativeCompressions": 0,
"coherenceIssues": 0,
"messages": []
"messages": [],
"overheadRatio": 0.000018653536585363587
},
"Entity-dense technical": {
"ratio": 1.5571321882001494,
Expand Down Expand Up @@ -1107,7 +1117,8 @@
"entityRetention": 0.6666666666666666,
"codeBlocksIntact": true
}
]
],
"overheadRatio": 0.00011654841402337068
},
"Prose-only conversation": {
"ratio": 3.367965367965368,
Expand Down Expand Up @@ -1167,7 +1178,8 @@
"entityRetention": 1,
"codeBlocksIntact": true
}
]
],
"overheadRatio": 0.000045656333830104156
},
"Mixed languages": {
"ratio": 1.0689134808853118,
Expand Down Expand Up @@ -1213,7 +1225,51 @@
"entityRetention": 0.6666666666666666,
"codeBlocksIntact": true
}
]
],
"overheadRatio": 0.00003091133004926051
},
"High-entropy content": {
"ratio": 1.3451492537313432,
"avgEntityRetention": 1,
"minEntityRetention": 1,
"codeBlockIntegrity": 1,
"informationDensity": 1,
"compressedQualityScore": 1,
"probesPassed": 4,
"probesTotal": 4,
"probePassRate": 1,
"probeResults": [
{
"label": "Hex block verbatim",
"passed": true
},
{
"label": "UUID array verbatim",
"passed": true
},
{
"label": "Base64 blob verbatim",
"passed": true
},
{
"label": "Mixed entropy+prose preserves entropy",
"passed": true
}
],
"negativeCompressions": 0,
"coherenceIssues": 1,
"messages": [
{
"messageId": "50042",
"action": "compressed",
"inputChars": 808,
"outputChars": 253,
"localRatio": 3.1936758893280635,
"entityRetention": 1,
"codeBlocksIntact": true
}
],
"overheadRatio": 0.000058397177419353755
}
},
"tradeoff": {
Expand Down
Loading
Loading