EvalHarness/build/lib/evalharness/fingerprint/references/minimax_m27_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

531 lines
13 KiB
JSON

{
"formatVersion": 1,
"protocol": "one-token/v1",
"model": "MiniMax/MiniMax-M2.7",
"collectedAt": "2026-09-02T03:28:10.920Z",
"samplesPerCell": 25,
"postReasoning": false,
"meta": {
"fusion": true,
"note": "26-cell fp_fusion reference: 16 detector + 10 fp-only cells.",
"sourceDetector": "minimax_m27_reference.json",
"sourceExtra": "/tmp/mm_extra_cells2.json"
},
"cells": {
"random-number-1-100:en": {
"cellId": "random-number-1-100:en",
"counts": {
"27": 1,
"42": 7,
"57": 1,
"58": 2,
"61": 1,
"73": 13
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 1.8535681581652277,
"normalizedEntropy": 0.2789898073076861,
"medianLatencyMs": null,
"meanCompletionTokens": 284.12,
"meanReasoningTokens": 0
},
"random-number-1-100:zh": {
"cellId": "random-number-1-100:zh",
"counts": {
"37": 1,
"42": 10,
"45": 1,
"47": 4,
"63": 1,
"71": 1,
"73": 7
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 2.2090255736436504,
"normalizedEntropy": 0.33249147942778584,
"medianLatencyMs": 5043.271206999998,
"meanCompletionTokens": 197.36,
"meanReasoningTokens": 0
},
"random-color:en": {
"cellId": "random-color:en",
"counts": {
"green": 2,
"cyan": 2,
"blue": 9,
"turquoise": 1,
"mauve": 1,
"magenta": 6,
"azure": 1,
"teal": 2,
"crimson": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 2.6422921890824145,
"normalizedEntropy": 0.5384860611009273,
"medianLatencyMs": null,
"meanCompletionTokens": 181.52,
"meanReasoningTokens": 0
},
"random-animal:en": {
"cellId": "random-animal:en",
"counts": {
"elephant": 11,
"giraffe": 5,
"penguin": 4,
"lion": 1,
"otter": 1,
"zebra": 1,
"dog": 1,
"panda": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 2.337320658596841,
"normalizedEntropy": 0.41413540317194647,
"medianLatencyMs": null,
"meanCompletionTokens": 133.72,
"meanReasoningTokens": 0
},
"random-number-1-10:en": {
"cellId": "random-number-1-10:en",
"counts": {
"3": 1,
"5": 1,
"7": 22,
"9": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.7195563653739032,
"normalizedEntropy": 0.21660804954849616,
"medianLatencyMs": null,
"meanCompletionTokens": 190.76,
"meanReasoningTokens": 0
},
"random-letter:en": {
"cellId": "random-letter:en",
"counts": {
"g": 4,
"k": 7,
"m": 6,
"q": 3,
"f": 1,
"x": 2,
"z": 1,
"r": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 2.647210311338979,
"normalizedEntropy": 0.5631835466631376,
"medianLatencyMs": null,
"meanCompletionTokens": 144.28,
"meanReasoningTokens": 0
},
"random-color:zh": {
"cellId": "random-color:zh",
"counts": {
"红": 8,
"蓝": 13,
"紫": 1,
"绿": 2,
"天蓝": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 1.6796275363413569,
"normalizedEntropy": 0.3422997728631977,
"medianLatencyMs": null,
"meanCompletionTokens": 177.52,
"meanReasoningTokens": 0
},
"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": null,
"meanCompletionTokens": 191.12,
"meanReasoningTokens": 0
},
"favorite-number:en": {
"cellId": "favorite-number:en",
"counts": {
"7": 22,
"42": 3
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.5293608652873644,
"normalizedEntropy": 0.039837942232197415,
"medianLatencyMs": null,
"meanCompletionTokens": 201.08,
"meanReasoningTokens": 0
},
"random-city:en": {
"cellId": "random-city:en",
"counts": {
"cairo": 1,
"bangkok": 1,
"paris": 7,
"barcelona": 1,
"tokyo": 11,
"lagos": 1,
"denver": 1,
"sydney": 1,
"mumbai": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 2.3356468993981845,
"normalizedEntropy": 0.4138388401231415,
"medianLatencyMs": null,
"meanCompletionTokens": 163.6,
"meanReasoningTokens": 0
},
"random-number-1-10:zh": {
"cellId": "random-number-1-10:zh",
"counts": {
"5": 5,
"7": 20
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.7219280948873623,
"normalizedEntropy": 0.2173220112736489,
"medianLatencyMs": null,
"meanCompletionTokens": 195.08,
"meanReasoningTokens": 0
},
"coin-flip:zh": {
"cellId": "coin-flip:zh",
"counts": {
"heads": 25
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0,
"normalizedEntropy": 0,
"medianLatencyMs": null,
"meanCompletionTokens": 126.04,
"meanReasoningTokens": 0
},
"random-letter:zh": {
"cellId": "random-letter:zh",
"counts": {
"m": 4,
"k": 6,
"g": 7,
"x": 3,
"l": 1,
"a": 1,
"q": 2,
"u": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 2.6472103113389793,
"normalizedEntropy": 0.5631835466631377,
"medianLatencyMs": null,
"meanCompletionTokens": 192.84,
"meanReasoningTokens": 0
},
"random-animal:zh": {
"cellId": "random-animal:zh",
"counts": {
"猫": 15,
"熊猫": 3,
"猫头鹰": 1,
"大象": 2,
"狗": 2,
"企鹅": 1,
"老虎": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 1.949526332323075,
"normalizedEntropy": 0.3454245230158656,
"medianLatencyMs": null,
"meanCompletionTokens": 182.88,
"meanReasoningTokens": 0
},
"random-city:zh": {
"cellId": "random-city:zh",
"counts": {
"深圳": 1,
"北京": 10,
"东京": 12,
"上海": 1,
"杭州": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 1.5943029514736247,
"normalizedEntropy": 0.2824846873954918,
"medianLatencyMs": null,
"meanCompletionTokens": 150.12,
"meanReasoningTokens": 0
},
"favorite-number:zh": {
"cellId": "favorite-number:zh",
"counts": {
"7": 25
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0,
"normalizedEntropy": 0,
"medianLatencyMs": null,
"meanCompletionTokens": 189.36,
"meanReasoningTokens": 0
},
"binary-season:en": {
"cellId": "binary-season:en",
"counts": {
"summer": 25
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": -0.0,
"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": 13,
"dog": 9
},
"validCount": 22,
"invalidCount": 3,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 1.0211917930491574,
"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": {
"sea": 16,
"mountain": 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": {
"coffee": 7,
"tea": 18
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 0.8554508105601306,
"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": 4,
"monday": 8,
"friday": 2,
"tuesday": 1,
"saturday": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 2.142683189255492,
"normalizedEntropy": 0.0,
"medianLatencyMs": null,
"meanCompletionTokens": null,
"meanReasoningTokens": null
},
"day-of-week:zh": {
"cellId": "day-of-week:zh",
"counts": {
"monday": 12,
"wednesday": 9,
"thursday": 1,
"friday": 1,
"tuesday": 1,
"saturday": 1
},
"validCount": 25,
"invalidCount": 0,
"refusalCount": 0,
"emptyCount": 0,
"errorCount": 0,
"totalCount": 25,
"entropyBits": 1.7819011889093375,
"normalizedEntropy": 0.0,
"medianLatencyMs": null,
"meanCompletionTokens": null,
"meanReasoningTokens": null
}
}
}