EvalHarness/build/lib/evalharness/fingerprint/references/glm53_fusion_reference.json
sora 370953729b Fix perf stats (wrong import path), per-repeat checkpoints, README
- perf_stats aggregator lives in eval/, not model/: the import failed
  silently and EVERY perf column was empty (not just ttft). Now warns
  on stderr instead of swallowing.
- repeats > 1 get their own checkpoint key (:rep2, :rep3, ...): repeat 2
  previously restored repeat 1's predictions and finished instantly with
  identical scores. rep1 keeps the legacy key (existing checkpoints still
  resume).
- repeats summary: report the MEAN score and aggregate time/tokens over
  ALL runs (was: last run only).
- README: six-benchmark command as the primary example.

Co-Authored-By: Claude <noreply@anthropic.com>
2026-09-11 13:38:04 +00:00

517 lines
13 KiB
JSON

{
"formatVersion": 1,
"protocol": "one-token/v1",
"model": "ZhipuAi/GLM-5.3",
"collectedAt": "2026-09-01T04:07:46.932Z",
"samplesPerCell": 25,
"postReasoning": false,
"meta": {
"fusion": true,
"note": "26-cell fp_fusion reference: 16 detector cells + 10 fp_fusion-only cells (binary preferences + day-of-week).",
"sourceDetector": "glm53_reference.json",
"sourceExtra": "/tmp/glm53_extra_cells.json"
},
"cells": {
"random-number-1-100:en": {
"cellId": "random-number-1-100:en",
"counts": {
"37": 1,
"42": 2,
"47": 16,
"57": 2,
"67": 1,
"73": 2,
"83": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 1.8438561897747248,
"normalizedEntropy": 0.27752801040644515,
"medianLatencyMs": 3048.427018000046,
"meanCompletionTokens": 75.44,
"meanReasoningTokens": 72.28
},
"random-number-1-100:zh": {
"cellId": "random-number-1-100:zh",
"counts": {
"37": 1,
"42": 7,
"47": 11,
"57": 1,
"63": 1,
"68": 1,
"73": 3
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 2.145451399311646,
"normalizedEntropy": 0.3229226127160336,
"medianLatencyMs": 3012.2534959999903,
"meanCompletionTokens": 59.72,
"meanReasoningTokens": 56.44
},
"random-color:en": {
"cellId": "random-color:en",
"counts": {
"teal": 16,
"turquoise": 6,
"periwinkle": 1,
"indigo": 2
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 1.3834651896016472,
"normalizedEntropy": 0.28194335346294375,
"medianLatencyMs": 3771.320187999998,
"meanCompletionTokens": 80.44,
"meanReasoningTokens": 76.32
},
"random-animal:en": {
"cellId": "random-animal:en",
"counts": {
"capybara": 13,
"axolotl": 2,
"hedgehog": 1,
"pangolin": 4,
"platypus": 3,
"okapi": 1,
"narwhal": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 2.1294320362548183,
"normalizedEntropy": 0.37730090290266854,
"medianLatencyMs": 4167.4443130000145,
"meanCompletionTokens": 76.16,
"meanReasoningTokens": 71
},
"random-number-1-10:en": {
"cellId": "random-number-1-10:en",
"counts": {
"4": 4,
"7": 21
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.6343095546405662,
"normalizedEntropy": 0.19094620248307148,
"medianLatencyMs": 2412.1367320000136,
"meanCompletionTokens": 65.76,
"meanReasoningTokens": 62.36
},
"random-letter:en": {
"cellId": "random-letter:en",
"counts": {
"k": 5,
"r": 6,
"q": 9,
"m": 2,
"j": 3
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 2.1477110700184037,
"normalizedEntropy": 0.45691705431928625,
"medianLatencyMs": 3700.4820349999936,
"meanCompletionTokens": 69.84,
"meanReasoningTokens": 66.8
},
"random-color:zh": {
"cellId": "random-color:zh",
"counts": {
"蓝": 16,
"青": 6,
"靛蓝": 1,
"紫": 2
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 1.3834651896016472,
"normalizedEntropy": 0.28194335346294375,
"medianLatencyMs": 3500.8726499999757,
"meanCompletionTokens": 70.04,
"meanReasoningTokens": 66.04
},
"coin-flip:en": {
"cellId": "coin-flip:en",
"counts": {
"heads": 23,
"tails": 2
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.4021791902022728,
"normalizedEntropy": 0.4021791902022728,
"medianLatencyMs": 3116.6536569999953,
"meanCompletionTokens": 75.84,
"meanReasoningTokens": 72.04
},
"favorite-number:en": {
"cellId": "favorite-number:en",
"counts": {
"7": 10,
"42": 15
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.9709505944546686,
"normalizedEntropy": 0.07307051999623161,
"medianLatencyMs": 7386.655828999996,
"meanCompletionTokens": 225.4,
"meanReasoningTokens": 222.08
},
"random-city:en": {
"cellId": "random-city:en",
"counts": {
"lisbon": 6,
"osaka": 2,
"nairobi": 2,
"barcelona": 4,
"copenhagen": 1,
"helsinki": 1,
"kyoto": 5,
"valencia": 1,
"oslo": 2,
"budapest": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 2.999079570624174,
"normalizedEntropy": 0.5313883752137,
"medianLatencyMs": 3566.0539570000255,
"meanCompletionTokens": 64.68,
"meanReasoningTokens": 60.4
},
"random-number-1-10:zh": {
"cellId": "random-number-1-10:zh",
"counts": {
"7": 25
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0,
"normalizedEntropy": 0,
"medianLatencyMs": 2703.40669600002,
"meanCompletionTokens": 54.96,
"meanReasoningTokens": 51.52
},
"coin-flip:zh": {
"cellId": "coin-flip:zh",
"counts": {
"heads": 24,
"tails": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.24229218908241482,
"normalizedEntropy": 0.24229218908241482,
"medianLatencyMs": 3555.5682660000166,
"meanCompletionTokens": 78.72,
"meanReasoningTokens": 75.28
},
"random-letter:zh": {
"cellId": "random-letter:zh",
"counts": {
"k": 8,
"q": 11,
"m": 4,
"r": 1,
"g": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 1.841706277574314,
"normalizedEntropy": 0.3918157423583902,
"medianLatencyMs": 3158.31832999998,
"meanCompletionTokens": 65.72,
"meanReasoningTokens": 62.56
},
"random-animal:zh": {
"cellId": "random-animal:zh",
"counts": {
"猫": 10,
"水獭": 4,
"斑马": 2,
"企鹅": 3,
"水豚": 4,
"鸭嘴兽": 1,
"袋鼠": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 2.4048894517332404,
"normalizedEntropy": 0.426107500061803,
"medianLatencyMs": 5038.485356999969,
"meanCompletionTokens": 105.2,
"meanReasoningTokens": 98.92
},
"random-city:zh": {
"cellId": "random-city:zh",
"counts": {
"布拉格": 2,
"北京": 4,
"京都": 2,
"成都": 5,
"巴黎": 4,
"杭州": 1,
"里斯本": 4,
"上海": 1,
"东京": 2
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 2.9794705707972517,
"normalizedEntropy": 0.5279139777153283,
"medianLatencyMs": 4077.9174099999946,
"meanCompletionTokens": 97.32,
"meanReasoningTokens": 93.76
},
"favorite-number:zh": {
"cellId": "favorite-number:zh",
"counts": {
"7": 12,
"42": 13
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.9988455359952018,
"normalizedEntropy": 0.07516980073746855,
"medianLatencyMs": null,
"meanCompletionTokens": 171.16,
"meanReasoningTokens": 169.16
},
"binary-season:en": {
"cellId": "binary-season:en",
"counts": {
"summer": 21,
"winter": 4
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.6343095546405662,
"normalizedEntropy": 0.0,
"medianLatencyMs": null,
"meanCompletionTokens": null,
"meanReasoningTokens": null
},
"binary-season:zh": {
"cellId": "binary-season:zh",
"counts": {},
"validCount": 0,
"invalidCount": 25,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.0,
"normalizedEntropy": 0.0,
"medianLatencyMs": null,
"meanCompletionTokens": null,
"meanReasoningTokens": null
},
"binary-pet:en": {
"cellId": "binary-pet:en",
"counts": {
"cat": 16,
"dog": 9
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.9426831892554922,
"normalizedEntropy": 0.0,
"medianLatencyMs": null,
"meanCompletionTokens": null,
"meanReasoningTokens": null
},
"binary-pet:zh": {
"cellId": "binary-pet:zh",
"counts": {},
"validCount": 0,
"invalidCount": 25,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.0,
"normalizedEntropy": 0.0,
"medianLatencyMs": null,
"meanCompletionTokens": null,
"meanReasoningTokens": null
},
"binary-sea-mountain:en": {
"cellId": "binary-sea-mountain:en",
"counts": {
"mountain": 16,
"sea": 9
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.9426831892554922,
"normalizedEntropy": 0.0,
"medianLatencyMs": null,
"meanCompletionTokens": null,
"meanReasoningTokens": null
},
"binary-sea-mountain:zh": {
"cellId": "binary-sea-mountain:zh",
"counts": {},
"validCount": 0,
"invalidCount": 25,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.0,
"normalizedEntropy": 0.0,
"medianLatencyMs": null,
"meanCompletionTokens": null,
"meanReasoningTokens": null
},
"binary-tea-coffee:en": {
"cellId": "binary-tea-coffee:en",
"counts": {
"tea": 19,
"coffee": 6
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.7950402793845223,
"normalizedEntropy": 0.0,
"medianLatencyMs": null,
"meanCompletionTokens": null,
"meanReasoningTokens": null
},
"binary-tea-coffee:zh": {
"cellId": "binary-tea-coffee:zh",
"counts": {},
"validCount": 0,
"invalidCount": 25,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.0,
"normalizedEntropy": 0.0,
"medianLatencyMs": null,
"meanCompletionTokens": null,
"meanReasoningTokens": null
},
"day-of-week:en": {
"cellId": "day-of-week:en",
"counts": {
"wednesday": 9,
"thursday": 16
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.9426831892554922,
"normalizedEntropy": 0.0,
"medianLatencyMs": null,
"meanCompletionTokens": null,
"meanReasoningTokens": null
},
"day-of-week:zh": {
"cellId": "day-of-week:zh",
"counts": {
"thursday": 9,
"wednesday": 14,
"friday": 2
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 1.290564432903234,
"normalizedEntropy": 0.0,
"medianLatencyMs": null,
"meanCompletionTokens": null,
"meanReasoningTokens": null
}
}
}