{
	"method": "Paired case-cluster percentile bootstrap",
	"replicates": 1000000,
	"seed": 20260514,
	"rng": "NumPy PCG64 multinomial case multiplicities",
	"numpy_version": "2.5.3",
	"family_model_count": 19,
	"available_models": [
		"claude-opus-5",
		"claude-opus-5-5",
		"claude-sonnet-5",
		"claude-sonnet-5-5",
		"gemini-3-1-pro-preview",
		"gpt-4-1",
		"gpt-5-6-luna",
		"gpt-5-6-sol",
		"gpt-6-1-sol",
		"gpt-6-luna",
		"gpt-6-sol",
		"grok-4-7",
		"muse-wonder-1-0"
	],
	"case_count": 91,
	"unit_count": 387,
	"familywise_alpha": 0.05,
	"interval_confidence": 0.9999025341130604,
	"correction": "Bonferroni across 171 model pairs and three metrics",
	"metrics": {
		"claude-opus-5": {
			"micro_brier": 0.13987105943152456,
			"equal_case_brier": 0.1354839407417979,
			"accuracy": 0.8010335917312662
		},
		"claude-opus-5-5": {
			"micro_brier": 0.14540258397932823,
			"equal_case_brier": 0.1476222901701473,
			"accuracy": 0.772609819121447
		},
		"claude-sonnet-5": {
			"micro_brier": 0.15848397932816535,
			"equal_case_brier": 0.15963922014493445,
			"accuracy": 0.7571059431524548
		},
		"claude-sonnet-5-5": {
			"micro_brier": 0.17297777777777776,
			"equal_case_brier": 0.1718345341959628,
			"accuracy": 0.7622739018087855
		},
		"gemini-3-1-pro-preview": {
			"micro_brier": 0.1834496124031007,
			"equal_case_brier": 0.1807985020931449,
			"accuracy": 0.7803617571059431
		},
		"gpt-4-1": {
			"micro_brier": 0.6051270671834625,
			"equal_case_brier": 0.5752195578231293,
			"accuracy": 0.39018087855297157
		},
		"gpt-5-6-luna": {
			"micro_brier": 0.14321692506459946,
			"equal_case_brier": 0.1508351081061795,
			"accuracy": 0.8087855297157622
		},
		"gpt-5-6-sol": {
			"micro_brier": 0.14009137209302328,
			"equal_case_brier": 0.13318617016079157,
			"accuracy": 0.8087855297157622
		},
		"gpt-6-1-sol": {
			"micro_brier": 0.14947861757105949,
			"equal_case_brier": 0.1388524223792081,
			"accuracy": 0.7855297157622739
		},
		"gpt-6-luna": {
			"micro_brier": 0.16367900516795866,
			"equal_case_brier": 0.17379408853051712,
			"accuracy": 0.7648578811369509
		},
		"gpt-6-sol": {
			"micro_brier": 0.1176279069767442,
			"equal_case_brier": 0.12949124213088506,
			"accuracy": 0.8449612403100775
		},
		"grok-4-7": {
			"micro_brier": 0.15832558139534886,
			"equal_case_brier": 0.16454140522176236,
			"accuracy": 0.7700258397932817
		},
		"muse-wonder-1-0": {
			"micro_brier": 0.16535968992248062,
			"equal_case_brier": 0.1690052697302697,
			"accuracy": 0.772609819121447
		}
	},
	"pairs": [
		{
			"model_a": "claude-opus-5",
			"model_b": "claude-opus-5-5",
			"metric": "micro_brier",
			"delta": -0.005531524547803673,
			"ci_low": -0.045155784167101705,
			"ci_high": 0.04098242627291337,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "claude-opus-5-5",
			"metric": "equal_case_brier",
			"delta": -0.012138349428349404,
			"ci_low": -0.04610249466823903,
			"ci_high": 0.022591720228289036,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "claude-opus-5-5",
			"metric": "accuracy",
			"delta": 0.02842377260981921,
			"ci_low": -0.062435641620075484,
			"ci_high": 0.1634877384196185,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "claude-sonnet-5",
			"metric": "micro_brier",
			"delta": -0.018612919896640795,
			"ci_low": -0.06223350673238699,
			"ci_high": 0.028481933734536957,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "claude-sonnet-5",
			"metric": "equal_case_brier",
			"delta": -0.024155279403136554,
			"ci_low": -0.07285360513160603,
			"ci_high": 0.022473300272103335,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "claude-sonnet-5",
			"metric": "accuracy",
			"delta": 0.043927648578811374,
			"ci_low": -0.13196580245539855,
			"ci_high": 0.1863989279428488,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "claude-sonnet-5-5",
			"metric": "micro_brier",
			"delta": -0.0331067183462532,
			"ci_low": -0.0760596413539885,
			"ci_high": 0.005042583832718196,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "claude-sonnet-5-5",
			"metric": "equal_case_brier",
			"delta": -0.036350593454164914,
			"ci_low": -0.08738024398220826,
			"ci_high": 0.0039659531461675385,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "claude-sonnet-5-5",
			"metric": "accuracy",
			"delta": 0.03875968992248069,
			"ci_low": -0.05760564265444545,
			"ci_high": 0.17222811341665054,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gemini-3-1-pro-preview",
			"metric": "micro_brier",
			"delta": -0.043578552971576145,
			"ci_low": -0.13276571315320376,
			"ci_high": 0.016482878124650928,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gemini-3-1-pro-preview",
			"metric": "equal_case_brier",
			"delta": -0.04531456135134701,
			"ci_low": -0.12960187854141478,
			"ci_high": 0.018943092113296173,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gemini-3-1-pro-preview",
			"metric": "accuracy",
			"delta": 0.02067183462532307,
			"ci_low": -0.09499999999999997,
			"ci_high": 0.15406868308395943,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-4-1",
			"metric": "micro_brier",
			"delta": -0.465256007751938,
			"ci_low": -0.6793760509485613,
			"ci_high": -0.2436123537843202,
			"significant": true
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-4-1",
			"metric": "equal_case_brier",
			"delta": -0.43973561708133135,
			"ci_low": -0.6272835414386158,
			"ci_high": -0.2492199670062592,
			"significant": true
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-4-1",
			"metric": "accuracy",
			"delta": 0.41085271317829464,
			"ci_low": 0.15931372549019615,
			"ci_high": 0.668285242738298,
			"significant": true
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-5-6-luna",
			"metric": "micro_brier",
			"delta": -0.0033458656330749015,
			"ci_low": -0.05757606181720394,
			"ci_high": 0.05148996785457754,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-5-6-luna",
			"metric": "equal_case_brier",
			"delta": -0.015351167364381607,
			"ci_low": -0.07604367362545553,
			"ci_high": 0.03389781863369744,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-5-6-luna",
			"metric": "accuracy",
			"delta": -0.007751937984496027,
			"ci_low": -0.16120701066937335,
			"ci_high": 0.11275964391691395,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-5-6-sol",
			"metric": "micro_brier",
			"delta": -0.0002203126614987172,
			"ci_low": -0.05157390638887942,
			"ci_high": 0.04810805820687639,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-5-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.002297770581006331,
			"ci_low": -0.05211407187628995,
			"ci_high": 0.053340328031424605,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-5-6-sol",
			"metric": "accuracy",
			"delta": -0.007751937984496027,
			"ci_low": -0.11853985067490524,
			"ci_high": 0.10584958217270193,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-6-1-sol",
			"metric": "micro_brier",
			"delta": -0.009607558139534927,
			"ci_low": -0.0560560018121286,
			"ci_high": 0.03335302134288452,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-6-1-sol",
			"metric": "equal_case_brier",
			"delta": -0.0033684816374102144,
			"ci_low": -0.05026561180274925,
			"ci_high": 0.03899662674504433,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-6-1-sol",
			"metric": "accuracy",
			"delta": 0.015503875968992276,
			"ci_low": -0.07176403904842323,
			"ci_high": 0.1007806860622045,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-6-luna",
			"metric": "micro_brier",
			"delta": -0.023807945736434105,
			"ci_low": -0.0806049135551415,
			"ci_high": 0.022217312732715943,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-6-luna",
			"metric": "equal_case_brier",
			"delta": -0.03831014778871922,
			"ci_low": -0.10868339824257822,
			"ci_high": 0.017067152461680796,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-6-luna",
			"metric": "accuracy",
			"delta": 0.03617571059431535,
			"ci_low": -0.05445585859826911,
			"ci_high": 0.13675937409489972,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-6-sol",
			"metric": "micro_brier",
			"delta": 0.022243152454780354,
			"ci_low": -0.03866177983730047,
			"ci_high": 0.11300188172196898,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.005992698610912839,
			"ci_low": -0.04213592007193931,
			"ci_high": 0.05575404765848271,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "gpt-6-sol",
			"metric": "accuracy",
			"delta": -0.04392764857881126,
			"ci_low": -0.24525601275356498,
			"ci_high": 0.09917947190001093,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "grok-4-7",
			"metric": "micro_brier",
			"delta": -0.0184545219638243,
			"ci_low": -0.07736586928653687,
			"ci_high": 0.029984114290450854,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "grok-4-7",
			"metric": "equal_case_brier",
			"delta": -0.029057464479964462,
			"ci_low": -0.09520706305082767,
			"ci_high": 0.02021881013519916,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "grok-4-7",
			"metric": "accuracy",
			"delta": 0.03100775193798455,
			"ci_low": -0.08535838843339508,
			"ci_high": 0.15660224762555253,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "muse-wonder-1-0",
			"metric": "micro_brier",
			"delta": -0.025488630490956066,
			"ci_low": -0.06307318205096189,
			"ci_high": 0.008196943693725872,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "muse-wonder-1-0",
			"metric": "equal_case_brier",
			"delta": -0.033521328988471794,
			"ci_low": -0.08467861398542975,
			"ci_high": 0.008064472728401596,
			"significant": false
		},
		{
			"model_a": "claude-opus-5",
			"model_b": "muse-wonder-1-0",
			"metric": "accuracy",
			"delta": 0.02842377260981921,
			"ci_low": -0.0560059855521156,
			"ci_high": 0.12348521767381779,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "claude-sonnet-5",
			"metric": "micro_brier",
			"delta": -0.013081395348837122,
			"ci_low": -0.06433301495756295,
			"ci_high": 0.04566383656004785,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "claude-sonnet-5",
			"metric": "equal_case_brier",
			"delta": -0.01201692997478715,
			"ci_low": -0.0623099378268974,
			"ci_high": 0.038096145826450524,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "claude-sonnet-5",
			"metric": "accuracy",
			"delta": 0.015503875968992165,
			"ci_low": -0.18275726933073425,
			"ci_high": 0.17236082693362378,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "claude-sonnet-5-5",
			"metric": "micro_brier",
			"delta": -0.027575193798449527,
			"ci_low": -0.07211716065761112,
			"ci_high": 0.011686156574054864,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "claude-sonnet-5-5",
			"metric": "equal_case_brier",
			"delta": -0.02421224402581551,
			"ci_low": -0.07234759866584968,
			"ci_high": 0.010771090995005082,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "claude-sonnet-5-5",
			"metric": "accuracy",
			"delta": 0.01033591731266148,
			"ci_low": -0.1372734525865118,
			"ci_high": 0.15260609121449234,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gemini-3-1-pro-preview",
			"metric": "micro_brier",
			"delta": -0.03804702842377247,
			"ci_low": -0.1310357568086574,
			"ci_high": 0.036469625187657416,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gemini-3-1-pro-preview",
			"metric": "equal_case_brier",
			"delta": -0.033176211922997606,
			"ci_low": -0.11622575786254268,
			"ci_high": 0.03570977829913893,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gemini-3-1-pro-preview",
			"metric": "accuracy",
			"delta": -0.007751937984496138,
			"ci_low": -0.15840555612112156,
			"ci_high": 0.1487543217575069,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-4-1",
			"metric": "micro_brier",
			"delta": -0.4597244832041343,
			"ci_low": -0.6679426359612761,
			"ci_high": -0.2383980699702064,
			"significant": true
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-4-1",
			"metric": "equal_case_brier",
			"delta": -0.427597267652982,
			"ci_low": -0.6105475215721519,
			"ci_high": -0.2417759524911075,
			"significant": true
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-4-1",
			"metric": "accuracy",
			"delta": 0.38242894056847543,
			"ci_low": 0.1308141277105808,
			"ci_high": 0.6393143329713022,
			"significant": true
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-5-6-luna",
			"metric": "micro_brier",
			"delta": 0.002185658914728772,
			"ci_low": -0.08001818407033386,
			"ci_high": 0.07051913334967286,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-5-6-luna",
			"metric": "equal_case_brier",
			"delta": -0.003212817936032203,
			"ci_low": -0.06373522418459777,
			"ci_high": 0.050210027840164394,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-5-6-luna",
			"metric": "accuracy",
			"delta": -0.036175710594315236,
			"ci_low": -0.21162296475987735,
			"ci_high": 0.10872980885718575,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-5-6-sol",
			"metric": "micro_brier",
			"delta": 0.005311211886304956,
			"ci_low": -0.07102640200034963,
			"ci_high": 0.06685865963745762,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-5-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.014436120009355735,
			"ci_low": -0.04123455555858623,
			"ci_high": 0.06586388128214153,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-5-6-sol",
			"metric": "accuracy",
			"delta": -0.036175710594315236,
			"ci_low": -0.18300849989177778,
			"ci_high": 0.09176735595196119,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-6-1-sol",
			"metric": "micro_brier",
			"delta": -0.004076033591731254,
			"ci_low": -0.07918162689041594,
			"ci_high": 0.055174049714035694,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-6-1-sol",
			"metric": "equal_case_brier",
			"delta": 0.00876986779093919,
			"ci_low": -0.038871743010748576,
			"ci_high": 0.052578456979502704,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-6-1-sol",
			"metric": "accuracy",
			"delta": -0.012919896640826933,
			"ci_low": -0.15507665983275165,
			"ci_high": 0.09218603614216038,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-6-luna",
			"metric": "micro_brier",
			"delta": -0.018276421188630432,
			"ci_low": -0.10534492408080548,
			"ci_high": 0.04901565041598423,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-6-luna",
			"metric": "equal_case_brier",
			"delta": -0.026171798360369813,
			"ci_low": -0.09564743684933483,
			"ci_high": 0.03611893013555105,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-6-luna",
			"metric": "accuracy",
			"delta": 0.007751937984496138,
			"ci_low": -0.14170083482860218,
			"ci_high": 0.11985664650624782,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-6-sol",
			"metric": "micro_brier",
			"delta": 0.027774677002584028,
			"ci_low": -0.03463805143297211,
			"ci_high": 0.08945499738684179,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.018131048039262243,
			"ci_low": -0.027982366842639387,
			"ci_high": 0.06096833063714725,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "gpt-6-sol",
			"metric": "accuracy",
			"delta": -0.07235142118863047,
			"ci_low": -0.2655806681776211,
			"ci_high": 0.06303447515119255,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "grok-4-7",
			"metric": "micro_brier",
			"delta": -0.012922997416020626,
			"ci_low": -0.072669998889599,
			"ci_high": 0.03633054769123484,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "grok-4-7",
			"metric": "equal_case_brier",
			"delta": -0.016919115051615058,
			"ci_low": -0.0723248044108148,
			"ci_high": 0.025814875285742396,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "grok-4-7",
			"metric": "accuracy",
			"delta": 0.0025839793281653423,
			"ci_low": -0.14841158771551205,
			"ci_high": 0.1333333333333333,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "muse-wonder-1-0",
			"metric": "micro_brier",
			"delta": -0.019957105943152392,
			"ci_low": -0.08814817166884156,
			"ci_high": 0.033385218524704,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "muse-wonder-1-0",
			"metric": "equal_case_brier",
			"delta": -0.02138297956012239,
			"ci_low": -0.07278290567134413,
			"ci_high": 0.025875530622469004,
			"significant": false
		},
		{
			"model_a": "claude-opus-5-5",
			"model_b": "muse-wonder-1-0",
			"metric": "accuracy",
			"delta": 0.0,
			"ci_low": -0.14828513767681528,
			"ci_high": 0.12468193384223925,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "claude-sonnet-5-5",
			"metric": "micro_brier",
			"delta": -0.014493798449612405,
			"ci_low": -0.08041613268220922,
			"ci_high": 0.044075410875143856,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "claude-sonnet-5-5",
			"metric": "equal_case_brier",
			"delta": -0.01219531405102836,
			"ci_low": -0.07981349403687368,
			"ci_high": 0.04819191858215468,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "claude-sonnet-5-5",
			"metric": "accuracy",
			"delta": -0.0051679586563306845,
			"ci_low": -0.17635182389615262,
			"ci_high": 0.19541009117402391,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gemini-3-1-pro-preview",
			"metric": "micro_brier",
			"delta": -0.02496563307493535,
			"ci_low": -0.11768757719820734,
			"ci_high": 0.05412544139582613,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gemini-3-1-pro-preview",
			"metric": "equal_case_brier",
			"delta": -0.021159281948210457,
			"ci_low": -0.11952970685835683,
			"ci_high": 0.06664869918411957,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gemini-3-1-pro-preview",
			"metric": "accuracy",
			"delta": -0.023255813953488302,
			"ci_low": -0.16118177387914237,
			"ci_high": 0.10685490129171163,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-4-1",
			"metric": "micro_brier",
			"delta": -0.44664308785529716,
			"ci_low": -0.6646111293589798,
			"ci_high": -0.21650861135820346,
			"significant": true
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-4-1",
			"metric": "equal_case_brier",
			"delta": -0.4155803376781948,
			"ci_low": -0.6075231097975751,
			"ci_high": -0.22061193521807887,
			"significant": true
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-4-1",
			"metric": "accuracy",
			"delta": 0.36692506459948326,
			"ci_low": 0.09186535356796902,
			"ci_high": 0.634407492003845,
			"significant": true
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-5-6-luna",
			"metric": "micro_brier",
			"delta": 0.015267054263565893,
			"ci_low": -0.03892896309731283,
			"ci_high": 0.06708553341510634,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-5-6-luna",
			"metric": "equal_case_brier",
			"delta": 0.008804112038754947,
			"ci_low": -0.054305925729554415,
			"ci_high": 0.07187082282088265,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-5-6-luna",
			"metric": "accuracy",
			"delta": -0.0516795865633074,
			"ci_low": -0.18056555500386187,
			"ci_high": 0.04806874559052664,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-5-6-sol",
			"metric": "micro_brier",
			"delta": 0.018392607235142078,
			"ci_low": -0.04155186620640872,
			"ci_high": 0.08107073568597531,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-5-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.026453049984142885,
			"ci_low": -0.04204659052912733,
			"ci_high": 0.09305909735790957,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-5-6-sol",
			"metric": "accuracy",
			"delta": -0.0516795865633074,
			"ci_low": -0.18785424762307582,
			"ci_high": 0.07476568353874681,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-6-1-sol",
			"metric": "micro_brier",
			"delta": 0.009005361757105868,
			"ci_low": -0.055821005809866105,
			"ci_high": 0.07098362592235641,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-6-1-sol",
			"metric": "equal_case_brier",
			"delta": 0.02078679776572634,
			"ci_low": -0.04360054909947507,
			"ci_high": 0.08606139564862898,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-6-1-sol",
			"metric": "accuracy",
			"delta": -0.028423772609819098,
			"ci_low": -0.17160973650744069,
			"ci_high": 0.14021651350598782,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-6-luna",
			"metric": "micro_brier",
			"delta": -0.00519502583979331,
			"ci_low": -0.066626825835824,
			"ci_high": 0.05118438210955737,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-6-luna",
			"metric": "equal_case_brier",
			"delta": -0.014154868385582664,
			"ci_low": -0.07502125557024424,
			"ci_high": 0.04321294020604551,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-6-luna",
			"metric": "accuracy",
			"delta": -0.007751937984496027,
			"ci_low": -0.14824301497557302,
			"ci_high": 0.1626091361704237,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-6-sol",
			"metric": "micro_brier",
			"delta": 0.04085607235142115,
			"ci_low": -0.018848087831677695,
			"ci_high": 0.12281499635850433,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.030147978014049392,
			"ci_low": -0.022809722183674695,
			"ci_high": 0.08605914384242619,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "gpt-6-sol",
			"metric": "accuracy",
			"delta": -0.08785529715762264,
			"ci_low": -0.29294703156507684,
			"ci_high": 0.037683104692034,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "grok-4-7",
			"metric": "micro_brier",
			"delta": 0.00015839793281649528,
			"ci_low": -0.06405533404237777,
			"ci_high": 0.06134903439437015,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "grok-4-7",
			"metric": "equal_case_brier",
			"delta": -0.0049021850768279085,
			"ci_low": -0.07777603477068043,
			"ci_high": 0.06009089572317067,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "grok-4-7",
			"metric": "accuracy",
			"delta": -0.012919896640826822,
			"ci_low": -0.15369933999662613,
			"ci_high": 0.12822305713942758,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "muse-wonder-1-0",
			"metric": "micro_brier",
			"delta": -0.006875710594315271,
			"ci_low": -0.06859129510414097,
			"ci_high": 0.046824254815975366,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "muse-wonder-1-0",
			"metric": "equal_case_brier",
			"delta": -0.00936604958533524,
			"ci_low": -0.07356127398165746,
			"ci_high": 0.04998965742976822,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5",
			"model_b": "muse-wonder-1-0",
			"metric": "accuracy",
			"delta": -0.015503875968992165,
			"ci_low": -0.15895134132960007,
			"ci_high": 0.1569231744839185,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gemini-3-1-pro-preview",
			"metric": "micro_brier",
			"delta": -0.010471834625322946,
			"ci_low": -0.11598170566587974,
			"ci_high": 0.07146955096135102,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gemini-3-1-pro-preview",
			"metric": "equal_case_brier",
			"delta": -0.008963967897182096,
			"ci_low": -0.10037883355726356,
			"ci_high": 0.07494652498989611,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gemini-3-1-pro-preview",
			"metric": "accuracy",
			"delta": -0.018087855297157618,
			"ci_low": -0.17234334196900128,
			"ci_high": 0.14734732549043925,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-4-1",
			"metric": "micro_brier",
			"delta": -0.43214928940568476,
			"ci_low": -0.6347561298627002,
			"ci_high": -0.22205441877215532,
			"significant": true
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-4-1",
			"metric": "equal_case_brier",
			"delta": -0.40338502362716644,
			"ci_low": -0.5799917607919441,
			"ci_high": -0.22404155462832603,
			"significant": true
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-4-1",
			"metric": "accuracy",
			"delta": 0.37209302325581395,
			"ci_low": 0.12335018241599432,
			"ci_high": 0.6270389923217796,
			"significant": true
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-5-6-luna",
			"metric": "micro_brier",
			"delta": 0.0297608527131783,
			"ci_low": -0.04591612171543288,
			"ci_high": 0.10380859011760933,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-5-6-luna",
			"metric": "equal_case_brier",
			"delta": 0.020999426089783307,
			"ci_low": -0.05261962484142845,
			"ci_high": 0.09151649605261476,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-5-6-luna",
			"metric": "accuracy",
			"delta": -0.046511627906976716,
			"ci_low": -0.224221695751768,
			"ci_high": 0.11333784982300683,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-5-6-sol",
			"metric": "micro_brier",
			"delta": 0.03288640568475448,
			"ci_low": -0.038271977424459314,
			"ci_high": 0.10422078374164101,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-5-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.038648364035171245,
			"ci_low": -0.02671001481351154,
			"ci_high": 0.10772453069439632,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-5-6-sol",
			"metric": "accuracy",
			"delta": -0.046511627906976716,
			"ci_low": -0.1983810863208746,
			"ci_high": 0.10130795169742658,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-6-1-sol",
			"metric": "micro_brier",
			"delta": 0.023499160206718273,
			"ci_low": -0.043766954579027004,
			"ci_high": 0.0896799284569906,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-6-1-sol",
			"metric": "equal_case_brier",
			"delta": 0.0329821118167547,
			"ci_low": -0.029296310415696452,
			"ci_high": 0.09880975738579738,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-6-1-sol",
			"metric": "accuracy",
			"delta": -0.023255813953488413,
			"ci_low": -0.16980723858944505,
			"ci_high": 0.09915639513176765,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-6-luna",
			"metric": "micro_brier",
			"delta": 0.009298772609819095,
			"ci_low": -0.06799545316249135,
			"ci_high": 0.07743661437058971,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-6-luna",
			"metric": "equal_case_brier",
			"delta": -0.001959554334554303,
			"ci_low": -0.08432554779003368,
			"ci_high": 0.07373188582319008,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-6-luna",
			"metric": "accuracy",
			"delta": -0.0025839793281653423,
			"ci_low": -0.15534323214846704,
			"ci_high": 0.12865294344492528,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-6-sol",
			"metric": "micro_brier",
			"delta": 0.055349870801033554,
			"ci_low": -0.021895368921194352,
			"ci_high": 0.14366809775588094,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.04234329206507775,
			"ci_low": -0.019338409835308816,
			"ci_high": 0.10747726080232954,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "gpt-6-sol",
			"metric": "accuracy",
			"delta": -0.08268733850129195,
			"ci_low": -0.2755643844278025,
			"ci_high": 0.0702247191011236,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "grok-4-7",
			"metric": "micro_brier",
			"delta": 0.0146521963824289,
			"ci_low": -0.0503303594628075,
			"ci_high": 0.07311741852693032,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "grok-4-7",
			"metric": "equal_case_brier",
			"delta": 0.007293128974200452,
			"ci_low": -0.06265958875189137,
			"ci_high": 0.07130032406602616,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "grok-4-7",
			"metric": "accuracy",
			"delta": -0.007751937984496138,
			"ci_low": -0.1638888888888889,
			"ci_high": 0.14002785018309208,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "muse-wonder-1-0",
			"metric": "micro_brier",
			"delta": 0.007618087855297134,
			"ci_low": -0.052262447252396635,
			"ci_high": 0.06225141685374636,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "muse-wonder-1-0",
			"metric": "equal_case_brier",
			"delta": 0.002829264465693121,
			"ci_low": -0.05320611325756533,
			"ci_high": 0.05230687012967239,
			"significant": false
		},
		{
			"model_a": "claude-sonnet-5-5",
			"model_b": "muse-wonder-1-0",
			"metric": "accuracy",
			"delta": -0.01033591731266148,
			"ci_low": -0.1600263157894737,
			"ci_high": 0.12686567164179108,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-4-1",
			"metric": "micro_brier",
			"delta": -0.42167745478036184,
			"ci_low": -0.6501689983050417,
			"ci_high": -0.18267154189577978,
			"significant": true
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-4-1",
			"metric": "equal_case_brier",
			"delta": -0.39442105572998437,
			"ci_low": -0.5994096278797957,
			"ci_high": -0.18301767833385837,
			"significant": true
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-4-1",
			"metric": "accuracy",
			"delta": 0.39018087855297157,
			"ci_low": 0.13487240261901953,
			"ci_high": 0.6387334828802358,
			"significant": true
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-5-6-luna",
			"metric": "micro_brier",
			"delta": 0.040232687338501244,
			"ci_low": -0.03459599851190474,
			"ci_high": 0.13847703780225423,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-5-6-luna",
			"metric": "equal_case_brier",
			"delta": 0.029963393986965403,
			"ci_low": -0.04577308251992367,
			"ci_high": 0.1182277359928706,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-5-6-luna",
			"metric": "accuracy",
			"delta": -0.028423772609819098,
			"ci_low": -0.15911272193546278,
			"ci_high": 0.08216333987594367,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-5-6-sol",
			"metric": "micro_brier",
			"delta": 0.04335824031007743,
			"ci_low": -0.018831246411381012,
			"ci_high": 0.12355970397659159,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-5-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.04761233193235334,
			"ci_low": -0.018974126103808536,
			"ci_high": 0.12948231890886797,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-5-6-sol",
			"metric": "accuracy",
			"delta": -0.028423772609819098,
			"ci_low": -0.11401414667304298,
			"ci_high": 0.04201730963606387,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-6-1-sol",
			"metric": "micro_brier",
			"delta": 0.03397099483204122,
			"ci_low": -0.02438756179690193,
			"ci_high": 0.11761250428966065,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-6-1-sol",
			"metric": "equal_case_brier",
			"delta": 0.041946079713936796,
			"ci_low": -0.010453840064905844,
			"ci_high": 0.11369856165138251,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-6-1-sol",
			"metric": "accuracy",
			"delta": -0.0051679586563307955,
			"ci_low": -0.11168233894759579,
			"ci_high": 0.09484890686966735,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-6-luna",
			"metric": "micro_brier",
			"delta": 0.01977060723514204,
			"ci_low": -0.05661737380352579,
			"ci_high": 0.12067299342979512,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-6-luna",
			"metric": "equal_case_brier",
			"delta": 0.007004413562627793,
			"ci_low": -0.07776044234039765,
			"ci_high": 0.10038421118308619,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-6-luna",
			"metric": "accuracy",
			"delta": 0.015503875968992276,
			"ci_low": -0.1349919450204802,
			"ci_high": 0.1428571428571429,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-6-sol",
			"metric": "micro_brier",
			"delta": 0.0658217054263565,
			"ci_low": -0.012876754682125121,
			"ci_high": 0.1774527670023215,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.05130725996225985,
			"ci_low": -0.015537654409291628,
			"ci_high": 0.13549742126347356,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "gpt-6-sol",
			"metric": "accuracy",
			"delta": -0.06459948320413433,
			"ci_low": -0.2347066736257142,
			"ci_high": 0.0625,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "grok-4-7",
			"metric": "micro_brier",
			"delta": 0.025124031007751846,
			"ci_low": -0.04924297666563033,
			"ci_high": 0.12502109163386407,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "grok-4-7",
			"metric": "equal_case_brier",
			"delta": 0.016257096871382548,
			"ci_low": -0.06111583725380716,
			"ci_high": 0.0965561780760014,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "grok-4-7",
			"metric": "accuracy",
			"delta": 0.01033591731266148,
			"ci_low": -0.13681646311721107,
			"ci_high": 0.1267960998942625,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "muse-wonder-1-0",
			"metric": "micro_brier",
			"delta": 0.01808992248062008,
			"ci_low": -0.046076172633833616,
			"ci_high": 0.10376253268628631,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "muse-wonder-1-0",
			"metric": "equal_case_brier",
			"delta": 0.011793232362875217,
			"ci_low": -0.06132474307694183,
			"ci_high": 0.09677410932723403,
			"significant": false
		},
		{
			"model_a": "gemini-3-1-pro-preview",
			"model_b": "muse-wonder-1-0",
			"metric": "accuracy",
			"delta": 0.007751937984496138,
			"ci_low": -0.09809976317877317,
			"ci_high": 0.11080532383965849,
			"significant": false
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "gpt-5-6-luna",
			"metric": "micro_brier",
			"delta": 0.46191014211886305,
			"ci_low": 0.22910849872300515,
			"ci_high": 0.6851495368340741,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "gpt-5-6-luna",
			"metric": "equal_case_brier",
			"delta": 0.4243844497169498,
			"ci_low": 0.21945033603066724,
			"ci_high": 0.6247031550886545,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "gpt-5-6-luna",
			"metric": "accuracy",
			"delta": -0.41860465116279066,
			"ci_low": -0.6694110703671747,
			"ci_high": -0.16653456712997422,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "gpt-5-6-sol",
			"metric": "micro_brier",
			"delta": 0.4650356950904393,
			"ci_low": 0.22307328707531793,
			"ci_high": 0.6932046668484393,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "gpt-5-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.4420333876623377,
			"ci_low": 0.23567416882584213,
			"ci_high": 0.6435222897353992,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "gpt-5-6-sol",
			"metric": "accuracy",
			"delta": -0.41860465116279066,
			"ci_low": -0.6697250939849625,
			"ci_high": -0.15942894419909817,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "gpt-6-1-sol",
			"metric": "micro_brier",
			"delta": 0.45564844961240303,
			"ci_low": 0.2138871913684027,
			"ci_high": 0.6846994951132366,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "gpt-6-1-sol",
			"metric": "equal_case_brier",
			"delta": 0.43636713544392114,
			"ci_low": 0.2280451913273913,
			"ci_high": 0.6394397424453567,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "gpt-6-1-sol",
			"metric": "accuracy",
			"delta": -0.39534883720930236,
			"ci_low": -0.6583184999625389,
			"ci_high": -0.1297883404122704,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "gpt-6-luna",
			"metric": "micro_brier",
			"delta": 0.4414480620155039,
			"ci_low": 0.19670215327958368,
			"ci_high": 0.6754239432374242,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "gpt-6-luna",
			"metric": "equal_case_brier",
			"delta": 0.40142546929261214,
			"ci_low": 0.18510452784277132,
			"ci_high": 0.6114366696635228,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "gpt-6-luna",
			"metric": "accuracy",
			"delta": -0.3746770025839793,
			"ci_low": -0.6465968947793213,
			"ci_high": -0.10064584828753892,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "gpt-6-sol",
			"metric": "micro_brier",
			"delta": 0.48749916020671835,
			"ci_low": 0.23760397023847854,
			"ci_high": 0.7119914884553351,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "gpt-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.44572831569224425,
			"ci_low": 0.23919160024707975,
			"ci_high": 0.6456332535380875,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "gpt-6-sol",
			"metric": "accuracy",
			"delta": -0.4547803617571059,
			"ci_low": -0.7120750599211015,
			"ci_high": -0.16579855061961576,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "grok-4-7",
			"metric": "micro_brier",
			"delta": 0.4468014857881137,
			"ci_low": 0.21903512459440916,
			"ci_high": 0.6622268891573118,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "grok-4-7",
			"metric": "equal_case_brier",
			"delta": 0.4106781526013669,
			"ci_low": 0.20313468009710628,
			"ci_high": 0.6095085261565939,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "grok-4-7",
			"metric": "accuracy",
			"delta": -0.3798449612403101,
			"ci_low": -0.6345627017862961,
			"ci_high": -0.12158434350322093,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "muse-wonder-1-0",
			"metric": "micro_brier",
			"delta": 0.4397673772609819,
			"ci_low": 0.21619582125263007,
			"ci_high": 0.6573027030892503,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "muse-wonder-1-0",
			"metric": "equal_case_brier",
			"delta": 0.4062142880928596,
			"ci_low": 0.20688351166627872,
			"ci_high": 0.5985263605777187,
			"significant": true
		},
		{
			"model_a": "gpt-4-1",
			"model_b": "muse-wonder-1-0",
			"metric": "accuracy",
			"delta": -0.38242894056847543,
			"ci_low": -0.6400565302144249,
			"ci_high": -0.12924653528361432,
			"significant": true
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "gpt-5-6-sol",
			"metric": "micro_brier",
			"delta": 0.0031255529715761843,
			"ci_low": -0.04766868510449514,
			"ci_high": 0.05133874688498051,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "gpt-5-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.017648937945387938,
			"ci_low": -0.04415168049067169,
			"ci_high": 0.07974472843879188,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "gpt-5-6-sol",
			"metric": "accuracy",
			"delta": 0.0,
			"ci_low": -0.09215105244996552,
			"ci_high": 0.1,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "gpt-6-1-sol",
			"metric": "micro_brier",
			"delta": -0.006261692506460026,
			"ci_low": -0.06119360874751157,
			"ci_high": 0.0401398675707436,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "gpt-6-1-sol",
			"metric": "equal_case_brier",
			"delta": 0.011982685726971393,
			"ci_low": -0.04223679425800808,
			"ci_high": 0.06466888667008877,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "gpt-6-1-sol",
			"metric": "accuracy",
			"delta": 0.023255813953488302,
			"ci_low": -0.0730337078651685,
			"ci_high": 0.16308278402457968,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "gpt-6-luna",
			"metric": "micro_brier",
			"delta": -0.020462080103359204,
			"ci_low": -0.06640802349049715,
			"ci_high": 0.017291213180358242,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "gpt-6-luna",
			"metric": "equal_case_brier",
			"delta": -0.02295898042433761,
			"ci_low": -0.08198378942830353,
			"ci_high": 0.022153141985679244,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "gpt-6-luna",
			"metric": "accuracy",
			"delta": 0.043927648578811374,
			"ci_low": -0.052039204314978195,
			"ci_high": 0.18643284546836925,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "gpt-6-sol",
			"metric": "micro_brier",
			"delta": 0.025589018087855256,
			"ci_low": -0.03648396008652134,
			"ci_high": 0.1417035983030681,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "gpt-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.021343865975294446,
			"ci_low": -0.0319658627783558,
			"ci_high": 0.07683999456908074,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "gpt-6-sol",
			"metric": "accuracy",
			"delta": -0.036175710594315236,
			"ci_low": -0.233622174375472,
			"ci_high": 0.08436282276725621,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "grok-4-7",
			"metric": "micro_brier",
			"delta": -0.015108656330749398,
			"ci_low": -0.07912445043037097,
			"ci_high": 0.04826066164171178,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "grok-4-7",
			"metric": "equal_case_brier",
			"delta": -0.013706297115582855,
			"ci_low": -0.07078491793341377,
			"ci_high": 0.03863461044954525,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "grok-4-7",
			"metric": "accuracy",
			"delta": 0.03875968992248058,
			"ci_low": -0.09922709335064651,
			"ci_high": 0.1763705616573212,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "muse-wonder-1-0",
			"metric": "micro_brier",
			"delta": -0.022142764857881164,
			"ci_low": -0.0836187494748188,
			"ci_high": 0.02443971645418435,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "muse-wonder-1-0",
			"metric": "equal_case_brier",
			"delta": -0.018170161624090186,
			"ci_low": -0.07212466528928464,
			"ci_high": 0.0354502330506281,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-luna",
			"model_b": "muse-wonder-1-0",
			"metric": "accuracy",
			"delta": 0.036175710594315236,
			"ci_low": -0.06036745406824143,
			"ci_high": 0.17994858611825193,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-sol",
			"model_b": "gpt-6-1-sol",
			"metric": "micro_brier",
			"delta": -0.00938724547803621,
			"ci_low": -0.04179590432599096,
			"ci_high": 0.022517564663113974,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-sol",
			"model_b": "gpt-6-1-sol",
			"metric": "equal_case_brier",
			"delta": -0.005666252218416545,
			"ci_low": -0.039936166736591554,
			"ci_high": 0.030753897740177796,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-sol",
			"model_b": "gpt-6-1-sol",
			"metric": "accuracy",
			"delta": 0.023255813953488302,
			"ci_low": -0.04971191730902323,
			"ci_high": 0.10699155765136098,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-sol",
			"model_b": "gpt-6-luna",
			"metric": "micro_brier",
			"delta": -0.023587633074935388,
			"ci_low": -0.06906057610290352,
			"ci_high": 0.023000328090389894,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-sol",
			"model_b": "gpt-6-luna",
			"metric": "equal_case_brier",
			"delta": -0.04060791836972555,
			"ci_low": -0.11324479064206466,
			"ci_high": 0.020750422204942325,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-sol",
			"model_b": "gpt-6-luna",
			"metric": "accuracy",
			"delta": 0.043927648578811374,
			"ci_low": -0.06216216216216219,
			"ci_high": 0.15027744251655445,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-sol",
			"model_b": "gpt-6-sol",
			"metric": "micro_brier",
			"delta": 0.02246346511627907,
			"ci_low": -0.030235223311027095,
			"ci_high": 0.1296054420471183,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-sol",
			"model_b": "gpt-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.003694928029906508,
			"ci_low": -0.041549419535881815,
			"ci_high": 0.05437996558315617,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-sol",
			"model_b": "gpt-6-sol",
			"metric": "accuracy",
			"delta": -0.036175710594315236,
			"ci_low": -0.20278239535234924,
			"ci_high": 0.08497720217155912,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-sol",
			"model_b": "grok-4-7",
			"metric": "micro_brier",
			"delta": -0.018234209302325582,
			"ci_low": -0.07942066856849005,
			"ci_high": 0.03994565930677977,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-sol",
			"model_b": "grok-4-7",
			"metric": "equal_case_brier",
			"delta": -0.03135523506097079,
			"ci_low": -0.0994950619701873,
			"ci_high": 0.027599417462170168,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-sol",
			"model_b": "grok-4-7",
			"metric": "accuracy",
			"delta": 0.03875968992248058,
			"ci_low": -0.08448988372058992,
			"ci_high": 0.1549785703293331,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-sol",
			"model_b": "muse-wonder-1-0",
			"metric": "micro_brier",
			"delta": -0.02526831782945735,
			"ci_low": -0.0781885190257392,
			"ci_high": 0.02507664696463221,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-sol",
			"model_b": "muse-wonder-1-0",
			"metric": "equal_case_brier",
			"delta": -0.035819099569478124,
			"ci_low": -0.1048074664618621,
			"ci_high": 0.027640070993312053,
			"significant": false
		},
		{
			"model_a": "gpt-5-6-sol",
			"model_b": "muse-wonder-1-0",
			"metric": "accuracy",
			"delta": 0.036175710594315236,
			"ci_low": -0.05416094546817735,
			"ci_high": 0.13577884489775946,
			"significant": false
		},
		{
			"model_a": "gpt-6-1-sol",
			"model_b": "gpt-6-luna",
			"metric": "micro_brier",
			"delta": -0.014200387596899178,
			"ci_low": -0.052618634140809036,
			"ci_high": 0.028732742040009574,
			"significant": false
		},
		{
			"model_a": "gpt-6-1-sol",
			"model_b": "gpt-6-luna",
			"metric": "equal_case_brier",
			"delta": -0.034941666151309,
			"ci_low": -0.09973228029155469,
			"ci_high": 0.022328549665587255,
			"significant": false
		},
		{
			"model_a": "gpt-6-1-sol",
			"model_b": "gpt-6-luna",
			"metric": "accuracy",
			"delta": 0.02067183462532307,
			"ci_low": -0.06353591160220987,
			"ci_high": 0.10205718607974458,
			"significant": false
		},
		{
			"model_a": "gpt-6-1-sol",
			"model_b": "gpt-6-sol",
			"metric": "micro_brier",
			"delta": 0.03185071059431528,
			"ci_low": -0.022201055502529123,
			"ci_high": 0.14252375713329468,
			"significant": false
		},
		{
			"model_a": "gpt-6-1-sol",
			"model_b": "gpt-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.009361180248323053,
			"ci_low": -0.031088872841600737,
			"ci_high": 0.056981975598806425,
			"significant": false
		},
		{
			"model_a": "gpt-6-1-sol",
			"model_b": "gpt-6-sol",
			"metric": "accuracy",
			"delta": -0.05943152454780354,
			"ci_low": -0.2557616589149888,
			"ci_high": 0.056603773584905676,
			"significant": false
		},
		{
			"model_a": "gpt-6-1-sol",
			"model_b": "grok-4-7",
			"metric": "micro_brier",
			"delta": -0.008846963824289372,
			"ci_low": -0.06646721876166477,
			"ci_high": 0.04270229784561683,
			"significant": false
		},
		{
			"model_a": "gpt-6-1-sol",
			"model_b": "grok-4-7",
			"metric": "equal_case_brier",
			"delta": -0.025688982842554248,
			"ci_low": -0.08390981055642877,
			"ci_high": 0.02060156636826258,
			"significant": false
		},
		{
			"model_a": "gpt-6-1-sol",
			"model_b": "grok-4-7",
			"metric": "accuracy",
			"delta": 0.015503875968992276,
			"ci_low": -0.10529929715372179,
			"ci_high": 0.13797489413188702,
			"significant": false
		},
		{
			"model_a": "gpt-6-1-sol",
			"model_b": "muse-wonder-1-0",
			"metric": "micro_brier",
			"delta": -0.01588107235142114,
			"ci_low": -0.05783536939388452,
			"ci_high": 0.029669463759797027,
			"significant": false
		},
		{
			"model_a": "gpt-6-1-sol",
			"model_b": "muse-wonder-1-0",
			"metric": "equal_case_brier",
			"delta": -0.03015284735106158,
			"ci_low": -0.08813580892345442,
			"ci_high": 0.027801001287664346,
			"significant": false
		},
		{
			"model_a": "gpt-6-1-sol",
			"model_b": "muse-wonder-1-0",
			"metric": "accuracy",
			"delta": 0.012919896640826933,
			"ci_low": -0.06254548795353507,
			"ci_high": 0.09221320652297281,
			"significant": false
		},
		{
			"model_a": "gpt-6-luna",
			"model_b": "gpt-6-sol",
			"metric": "micro_brier",
			"delta": 0.04605109819121446,
			"ci_low": -0.011180655832292117,
			"ci_high": 0.1631476773823759,
			"significant": false
		},
		{
			"model_a": "gpt-6-luna",
			"model_b": "gpt-6-sol",
			"metric": "equal_case_brier",
			"delta": 0.044302846399632057,
			"ci_low": -0.0035623315881591383,
			"ci_high": 0.10247233160402003,
			"significant": false
		},
		{
			"model_a": "gpt-6-luna",
			"model_b": "gpt-6-sol",
			"metric": "accuracy",
			"delta": -0.08010335917312661,
			"ci_low": -0.2839586211573522,
			"ci_high": 0.050169186351052455,
			"significant": false
		},
		{
			"model_a": "gpt-6-luna",
			"model_b": "grok-4-7",
			"metric": "micro_brier",
			"delta": 0.0053534237726098055,
			"ci_low": -0.06173574774312425,
			"ci_high": 0.06631465416098294,
			"significant": false
		},
		{
			"model_a": "gpt-6-luna",
			"model_b": "grok-4-7",
			"metric": "equal_case_brier",
			"delta": 0.009252683308754756,
			"ci_low": -0.05664244290217927,
			"ci_high": 0.0719957682438718,
			"significant": false
		},
		{
			"model_a": "gpt-6-luna",
			"model_b": "grok-4-7",
			"metric": "accuracy",
			"delta": -0.0051679586563307955,
			"ci_low": -0.1332150290981691,
			"ci_high": 0.1359935902112052,
			"significant": false
		},
		{
			"model_a": "gpt-6-luna",
			"model_b": "muse-wonder-1-0",
			"metric": "micro_brier",
			"delta": -0.0016806847545219605,
			"ci_low": -0.04569844760863203,
			"ci_high": 0.04259652791051264,
			"significant": false
		},
		{
			"model_a": "gpt-6-luna",
			"model_b": "muse-wonder-1-0",
			"metric": "equal_case_brier",
			"delta": 0.004788818800247424,
			"ci_low": -0.04742604482437988,
			"ci_high": 0.06214282985107242,
			"significant": false
		},
		{
			"model_a": "gpt-6-luna",
			"model_b": "muse-wonder-1-0",
			"metric": "accuracy",
			"delta": -0.007751937984496138,
			"ci_low": -0.08968513658220933,
			"ci_high": 0.07508772065762616,
			"significant": false
		},
		{
			"model_a": "gpt-6-sol",
			"model_b": "grok-4-7",
			"metric": "micro_brier",
			"delta": -0.040697674418604654,
			"ci_low": -0.1331061711234268,
			"ci_high": 0.02315891372717879,
			"significant": false
		},
		{
			"model_a": "gpt-6-sol",
			"model_b": "grok-4-7",
			"metric": "equal_case_brier",
			"delta": -0.0350501630908773,
			"ci_low": -0.09475738245223865,
			"ci_high": 0.010840053764220136,
			"significant": false
		},
		{
			"model_a": "gpt-6-sol",
			"model_b": "grok-4-7",
			"metric": "accuracy",
			"delta": 0.07493540051679581,
			"ci_low": -0.054172364672364665,
			"ci_high": 0.262675727146837,
			"significant": false
		},
		{
			"model_a": "gpt-6-sol",
			"model_b": "muse-wonder-1-0",
			"metric": "micro_brier",
			"delta": -0.04773178294573642,
			"ci_low": -0.15908507463014904,
			"ci_high": 0.02053907792545386,
			"significant": false
		},
		{
			"model_a": "gpt-6-sol",
			"model_b": "muse-wonder-1-0",
			"metric": "equal_case_brier",
			"delta": -0.03951402759938463,
			"ci_low": -0.09954093594818922,
			"ci_high": 0.016574087075786198,
			"significant": false
		},
		{
			"model_a": "gpt-6-sol",
			"model_b": "muse-wonder-1-0",
			"metric": "accuracy",
			"delta": 0.07235142118863047,
			"ci_low": -0.0716770789706362,
			"ci_high": 0.27572023595215284,
			"significant": false
		},
		{
			"model_a": "grok-4-7",
			"model_b": "muse-wonder-1-0",
			"metric": "micro_brier",
			"delta": -0.007034108527131766,
			"ci_low": -0.06962330019677562,
			"ci_high": 0.053171519371521196,
			"significant": false
		},
		{
			"model_a": "grok-4-7",
			"model_b": "muse-wonder-1-0",
			"metric": "equal_case_brier",
			"delta": -0.004463864508507331,
			"ci_low": -0.05724979846109407,
			"ci_high": 0.05597856022110884,
			"significant": false
		},
		{
			"model_a": "grok-4-7",
			"model_b": "muse-wonder-1-0",
			"metric": "accuracy",
			"delta": -0.0025839793281653423,
			"ci_low": -0.13000077970955565,
			"ci_high": 0.12736877879380767,
			"significant": false
		}
	],
	"significant_pairs": [
		{
			"better": "claude-opus-5",
			"worse": "gpt-4-1",
			"metric": "micro_brier"
		},
		{
			"better": "claude-opus-5",
			"worse": "gpt-4-1",
			"metric": "equal_case_brier"
		},
		{
			"better": "claude-opus-5",
			"worse": "gpt-4-1",
			"metric": "accuracy"
		},
		{
			"better": "claude-opus-5-5",
			"worse": "gpt-4-1",
			"metric": "micro_brier"
		},
		{
			"better": "claude-opus-5-5",
			"worse": "gpt-4-1",
			"metric": "equal_case_brier"
		},
		{
			"better": "claude-opus-5-5",
			"worse": "gpt-4-1",
			"metric": "accuracy"
		},
		{
			"better": "claude-sonnet-5",
			"worse": "gpt-4-1",
			"metric": "micro_brier"
		},
		{
			"better": "claude-sonnet-5",
			"worse": "gpt-4-1",
			"metric": "equal_case_brier"
		},
		{
			"better": "claude-sonnet-5",
			"worse": "gpt-4-1",
			"metric": "accuracy"
		},
		{
			"better": "claude-sonnet-5-5",
			"worse": "gpt-4-1",
			"metric": "micro_brier"
		},
		{
			"better": "claude-sonnet-5-5",
			"worse": "gpt-4-1",
			"metric": "equal_case_brier"
		},
		{
			"better": "claude-sonnet-5-5",
			"worse": "gpt-4-1",
			"metric": "accuracy"
		},
		{
			"better": "gemini-3-1-pro-preview",
			"worse": "gpt-4-1",
			"metric": "micro_brier"
		},
		{
			"better": "gemini-3-1-pro-preview",
			"worse": "gpt-4-1",
			"metric": "equal_case_brier"
		},
		{
			"better": "gemini-3-1-pro-preview",
			"worse": "gpt-4-1",
			"metric": "accuracy"
		},
		{
			"better": "gpt-5-6-luna",
			"worse": "gpt-4-1",
			"metric": "micro_brier"
		},
		{
			"better": "gpt-5-6-luna",
			"worse": "gpt-4-1",
			"metric": "equal_case_brier"
		},
		{
			"better": "gpt-5-6-luna",
			"worse": "gpt-4-1",
			"metric": "accuracy"
		},
		{
			"better": "gpt-5-6-sol",
			"worse": "gpt-4-1",
			"metric": "micro_brier"
		},
		{
			"better": "gpt-5-6-sol",
			"worse": "gpt-4-1",
			"metric": "equal_case_brier"
		},
		{
			"better": "gpt-5-6-sol",
			"worse": "gpt-4-1",
			"metric": "accuracy"
		},
		{
			"better": "gpt-6-1-sol",
			"worse": "gpt-4-1",
			"metric": "micro_brier"
		},
		{
			"better": "gpt-6-1-sol",
			"worse": "gpt-4-1",
			"metric": "equal_case_brier"
		},
		{
			"better": "gpt-6-1-sol",
			"worse": "gpt-4-1",
			"metric": "accuracy"
		},
		{
			"better": "gpt-6-luna",
			"worse": "gpt-4-1",
			"metric": "micro_brier"
		},
		{
			"better": "gpt-6-luna",
			"worse": "gpt-4-1",
			"metric": "equal_case_brier"
		},
		{
			"better": "gpt-6-luna",
			"worse": "gpt-4-1",
			"metric": "accuracy"
		},
		{
			"better": "gpt-6-sol",
			"worse": "gpt-4-1",
			"metric": "micro_brier"
		},
		{
			"better": "gpt-6-sol",
			"worse": "gpt-4-1",
			"metric": "equal_case_brier"
		},
		{
			"better": "gpt-6-sol",
			"worse": "gpt-4-1",
			"metric": "accuracy"
		},
		{
			"better": "grok-4-7",
			"worse": "gpt-4-1",
			"metric": "micro_brier"
		},
		{
			"better": "grok-4-7",
			"worse": "gpt-4-1",
			"metric": "equal_case_brier"
		},
		{
			"better": "grok-4-7",
			"worse": "gpt-4-1",
			"metric": "accuracy"
		},
		{
			"better": "muse-wonder-1-0",
			"worse": "gpt-4-1",
			"metric": "micro_brier"
		},
		{
			"better": "muse-wonder-1-0",
			"worse": "gpt-4-1",
			"metric": "equal_case_brier"
		},
		{
			"better": "muse-wonder-1-0",
			"worse": "gpt-4-1",
			"metric": "accuracy"
		}
	],
	"caveat": "Exploratory. Cross-case dependence has not been verified. Unavailable pairs are not tested.",
	"sources": {
		"gpt-6-sol": "gpt-6-sol.jsonl",
		"grok-4-7": "grok-4-7.jsonl",
		"gpt-6-luna": "gpt-6-luna.jsonl",
		"claude-opus-5-5": "claude-opus-5-5.jsonl",
		"gpt-4-1": "gpt-4-1.jsonl",
		"gemini-3-1-pro-preview": "gemini-3-1-pro-preview.jsonl",
		"gpt-6-1-sol": "gpt-6-1-sol.jsonl",
		"claude-sonnet-5-5": "claude-sonnet-5-5.jsonl",
		"claude-opus-5": "claude-opus-5.jsonl",
		"gpt-5-6-sol": "gpt-5-6-sol.jsonl",
		"claude-sonnet-5": "claude-sonnet-5.jsonl",
		"gpt-5-6-luna": "gpt-5-6-luna.jsonl",
		"muse-wonder-1-0": "muse-wonder-1-0.jsonl"
	},
	"provenance": {
		"release": "cycle-1-91-2026-09-08-luna-r5",
		"release_digest": "4311a6ee59c3ae1fcb392f1dd768ab00d1d7a7c7ea135271f3e117746233ed8a",
		"models": {
			"gpt-6-sol": {
				"score_run": "35885171489",
				"source": "native_unit_scores"
			},
			"grok-4-7": {
				"score_run": "35885175070",
				"source": "native_unit_scores"
			},
			"gpt-6-luna": {
				"score_run": "35940612024",
				"source": "native_unit_scores"
			},
			"claude-opus-5-5": {
				"score_run": "35954306953",
				"source": "native_unit_scores"
			},
			"gpt-4-1": {
				"score_run": "36073985227",
				"source": "native_unit_scores"
			},
			"gemini-3-1-pro-preview": {
				"score_run": "36169561374",
				"source": "native_unit_scores"
			},
			"gpt-6-1-sol": {
				"score_run": "36741462923",
				"source": "native_unit_scores"
			},
			"claude-sonnet-5-5": {
				"score_run": "36741468019",
				"source": "native_unit_scores"
			},
			"claude-opus-5": {
				"forecast_run": "34845972981",
				"source": "validated_receipts_joined_to_native_score_labels"
			},
			"gpt-5-6-sol": {
				"forecast_run": "34428487985",
				"source": "validated_receipts_joined_to_native_score_labels"
			},
			"claude-sonnet-5": {
				"forecast_run": "34895753581",
				"source": "validated_receipts_joined_to_native_score_labels"
			},
			"gpt-5-6-luna": {
				"forecast_run": "34222142006",
				"source": "recovered_native_unit_scores"
			},
			"muse-wonder-1-0": {
				"score_run": "38303872484",
				"forecast_run": "38300603621",
				"source": "native_unit_scores"
			}
		},
		"label_source_score_run": "36169561374",
		"cohort_validation": "All native score sources agree on 387 case/unit/outcome keys across 91 cases. Historical receipts bind to the same release and reproduce their prior published aggregates.",
		"coverage": "Thirteen of nineteen model configurations have recoverable unit-level evidence. The other six models and their pairs are not tested.",
		"recovered_note": "GPT-5.6 Luna's units are the native unit_scores output of its September 8, 2026 local scoring of run 34222142006, recovered from the operator's session record after the run's GitHub artifacts expired. They include a raw_output_sha256 per unit in the source record and reproduce the published aggregates exactly (micro Brier 0.143217, equal-case Brier 0.150835, 313 correct)."
	},
	"missing_models": [
		"claude-fable-5-1",
		"grok-4-6",
		"kimi-k3",
		"gpt-6-astra",
		"gemini-3-8-flash",
		"muse-spark-1-3"
	]
}
