{"cadence":{"daily":{"findings":[{"comparisons":172,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4524,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9429,"fixed_units":70,"gap":0.4905,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":9.645900194118998e-11,"paired_depth":14},{"comparisons":172,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3889,"dynamic_units":108,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":60,"gap":0.4111,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":3.062461648257195e-07,"paired_depth":12},{"comparisons":172,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8095,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.1905,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":9.702152402780321e-05,"paired_depth":14},{"comparisons":172,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.881,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.119,"level":"watch","metric":"tier_gap","model":"deepseek-v4.1-flash-1017@deepinfra","p":0.0026646624809190285,"paired_depth":14},{"comparisons":172,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.7407,"dynamic_units":54,"fdr_alpha":0.01,"fixed":0.9556,"fixed_units":45,"gap":0.2148,"level":"watch","metric":"tier_gap","model":"gemini-3.1-pro-preview","p":0.0038371046837955922,"paired_depth":9},{"comparisons":172,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.9048,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.0952,"level":"watch","metric":"tier_gap","model":"deepseek-chat@deepseek","p":0.007702164914128065,"paired_depth":14}],"latest_paired":"2026-11-09","verdict":"findings"},"weekly":{"findings":[{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.5397,"dynamic_units":63,"fdr_alpha":0.01,"fixed":0.9464,"fixed_units":168,"gap":0.4067,"level":"divergence","metric":"tier_gap","model":"deepseek-v4-flash-0731@deepinfra","p":1.1151477662060912e-13,"paired_depth":7},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8,"dynamic_units":90,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":240,"gap":0.2,"level":"divergence","metric":"tier_gap","model":"sarvam-105b@sarvam","p":1.0388965492545747e-12,"paired_depth":10},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8111,"dynamic_units":90,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":240,"gap":0.1889,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":4.730700819032354e-12,"paired_depth":10},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7917,"dynamic_units":72,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":192,"gap":0.2083,"level":"divergence","metric":"tier_gap","model":"claude-fable-5.1","p":7.402433956432056e-11,"paired_depth":8},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8333,"dynamic_units":72,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":192,"gap":0.1667,"level":"divergence","metric":"tier_gap","model":"claude-fable-5","p":7.039693686866462e-09,"paired_depth":8},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7444,"dynamic_units":90,"fdr_alpha":0.01,"fixed":0.95,"fixed_units":240,"gap":0.2056,"level":"divergence","metric":"tier_gap","model":"mistral-small@mistral","p":6.629865745003493e-08,"paired_depth":10},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8889,"dynamic_units":90,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":240,"gap":0.1111,"level":"divergence","metric":"tier_gap","model":"qwen3-235b@deepinfra","p":1.5709450561557817e-07,"paired_depth":10},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.9111,"dynamic_units":90,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":240,"gap":0.0889,"level":"divergence","metric":"tier_gap","model":"deepseek-chat@deepseek","p":2.927719720885413e-06,"paired_depth":10},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8889,"dynamic_units":90,"fdr_alpha":0.01,"fixed":0.9917,"fixed_units":240,"gap":0.1028,"level":"divergence","metric":"tier_gap","model":"gpt-5","p":8.912515504367887e-06,"paired_depth":10},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"tool-call","dynamic":0.7917,"dynamic_units":24,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":80,"gap":0.2083,"level":"divergence","metric":"tier_gap","model":"claude-fable-5","p":2.8603847837561514e-05,"paired_depth":8},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8889,"dynamic_units":90,"fdr_alpha":0.01,"fixed":0.9833,"fixed_units":240,"gap":0.0944,"level":"divergence","metric":"tier_gap","model":"llama-4-maverick@deepinfra","p":0.00015004765964046486,"paired_depth":10},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.8333,"dynamic_units":60,"fdr_alpha":0.01,"fixed":0.9688,"fixed_units":160,"gap":0.1354,"level":"divergence","metric":"tier_gap","model":"sarvam-105b@sarvam","p":0.00038681089957780777,"paired_depth":10},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.9556,"dynamic_units":90,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":240,"gap":0.0444,"level":"divergence","metric":"tier_gap","model":"gpt-5.6-terra","p":0.0010163473390919265,"paired_depth":10},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.375,"dynamic_units":48,"fdr_alpha":0.01,"fixed":0.625,"fixed_units":128,"gap":0.25,"level":"watch","metric":"tier_gap","model":"grok-4.7@xai","p":0.0029446602723225885,"paired_depth":8},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.9524,"dynamic_units":63,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":168,"gap":0.0476,"level":"watch","metric":"tier_gap","model":"claude-opus-5-5","p":0.004413691342121813,"paired_depth":7},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.9583,"dynamic_units":72,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":192,"gap":0.0417,"level":"watch","metric":"tier_gap","model":"claude-haiku-4-5","p":0.004446219930214165,"paired_depth":8},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8111,"dynamic_units":90,"fdr_alpha":0.01,"fixed":0.9167,"fixed_units":240,"gap":0.1056,"level":"watch","metric":"tier_gap","model":"gpt-5-mini","p":0.006796820650794981,"paired_depth":10},{"comparisons":124,"correction":"benjamini-hochberg","dimension":"tool-call","dynamic":0.9167,"dynamic_units":24,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":80,"gap":0.0833,"level":"watch","metric":"tier_gap","model":"claude-fable-5.1","p":0.0091291454719387,"paired_depth":8}],"latest_paired":"2026-11-08","verdict":"findings"}},"log":[{"cadence":"daily","date":"2026-09-18","finding":{"comparisons":68,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8111,"dynamic_units":90,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":50,"gap":0.1889,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":0.0010429204509780213,"paired_depth":10},"key":["2026-09-18","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-09-19","finding":{"comparisons":68,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8081,"dynamic_units":99,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":55,"gap":0.1919,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":0.0005203879349803708,"paired_depth":11},"key":["2026-09-19","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-09-20","finding":{"comparisons":68,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8056,"dynamic_units":108,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":60,"gap":0.1944,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":0.00026072963285531743,"paired_depth":12},"key":["2026-09-20","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-09-21","finding":{"comparisons":68,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8034,"dynamic_units":117,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":65,"gap":0.1966,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":0.0001310839688950848,"paired_depth":13},"key":["2026-09-21","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-09-22","finding":{"comparisons":68,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7937,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2063,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":4.486520279556613e-05,"paired_depth":14},"key":["2026-09-22","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-09-23","finding":{"comparisons":68,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7857,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2143,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":3.0339214284280612e-05,"paired_depth":14},"key":["2026-09-23","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-09-24","finding":{"comparisons":68,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7857,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2143,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":3.0339214284280612e-05,"paired_depth":14},"key":["2026-09-24","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-09-25","finding":{"comparisons":68,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7937,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2063,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":4.486520279556613e-05,"paired_depth":14},"key":["2026-09-25","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-09-26","finding":{"comparisons":68,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7698,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2302,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":1.3711517212922776e-05,"paired_depth":14},"key":["2026-09-26","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-09-27","finding":{"comparisons":68,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7778,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2222,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":2.0436806886962484e-05,"paired_depth":14},"key":["2026-09-27","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-09-28","finding":{"comparisons":68,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7698,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2302,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":1.3711517212922776e-05,"paired_depth":14},"key":["2026-09-28","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-09-29","finding":{"comparisons":68,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7619,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2381,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":9.16161721353686e-06,"paired_depth":14},"key":["2026-09-29","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-09-30","finding":{"comparisons":68,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7698,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2302,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":1.3711517212922776e-05,"paired_depth":14},"key":["2026-09-30","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-01","finding":{"comparisons":76,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.754,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.246,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":6.095702608804483e-06,"paired_depth":14},"key":["2026-10-01","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-01","finding":{"comparisons":76,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.381,"dynamic_units":42,"fdr_alpha":0.01,"fixed":0.8857,"fixed_units":35,"gap":0.5048,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":6.1106062422629165e-06,"paired_depth":7},"key":["2026-10-01","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-01","finding":{"comparisons":76,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8651,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.1349,"level":"divergence","metric":"tier_gap","model":"deepseek-chat@deepseek","p":0.0013007911271812748,"paired_depth":14},"key":["2026-10-01","daily","deepseek-chat@deepseek","capability"]},{"cadence":"daily","date":"2026-10-02","finding":{"comparisons":93,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.3958,"dynamic_units":48,"fdr_alpha":0.01,"fixed":0.875,"fixed_units":40,"gap":0.4792,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":4.293210495623262e-06,"paired_depth":8},"key":["2026-10-02","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-02","finding":{"comparisons":93,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.754,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.246,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":6.095702608804483e-06,"paired_depth":14},"key":["2026-10-02","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-03","finding":{"comparisons":95,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4074,"dynamic_units":54,"fdr_alpha":0.01,"fixed":0.8667,"fixed_units":45,"gap":0.4593,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":2.8874892270237392e-06,"paired_depth":9},"key":["2026-10-03","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-03","finding":{"comparisons":95,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.746,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.254,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":4.038234218531066e-06,"paired_depth":14},"key":["2026-10-03","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-04","finding":{"comparisons":95,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4,"dynamic_units":60,"fdr_alpha":0.01,"fixed":0.88,"fixed_units":50,"gap":0.48,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":2.474297799499994e-07,"paired_depth":10},"key":["2026-10-04","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-04","finding":{"comparisons":95,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.746,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.254,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":4.038234218531066e-06,"paired_depth":14},"key":["2026-10-04","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-05","finding":{"comparisons":99,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4,"dynamic_units":60,"fdr_alpha":0.01,"fixed":0.88,"fixed_units":50,"gap":0.48,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":2.474297799499994e-07,"paired_depth":10},"key":["2026-10-05","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-05","finding":{"comparisons":99,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.746,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.254,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":4.038234218531066e-06,"paired_depth":14},"key":["2026-10-05","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-05","finding":{"comparisons":99,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.381,"dynamic_units":63,"fdr_alpha":0.01,"fixed":0.7429,"fixed_units":35,"gap":0.3619,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":0.0005946449552088536,"paired_depth":7},"key":["2026-10-05","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-06","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.3889,"dynamic_units":72,"fdr_alpha":0.01,"fixed":0.9,"fixed_units":60,"gap":0.5111,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":1.6630076643779766e-09,"paired_depth":12},"key":["2026-10-06","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-06","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7619,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2381,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":9.16161721353686e-06,"paired_depth":14},"key":["2026-10-06","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-06","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3611,"dynamic_units":72,"fdr_alpha":0.01,"fixed":0.75,"fixed_units":40,"gap":0.3889,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":8.011587656029368e-05,"paired_depth":8},"key":["2026-10-06","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-07","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.3846,"dynamic_units":78,"fdr_alpha":0.01,"fixed":0.8923,"fixed_units":65,"gap":0.5077,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":5.17530839307098e-10,"paired_depth":13},"key":["2026-10-07","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-07","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7778,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2222,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":2.0436806886962484e-05,"paired_depth":14},"key":["2026-10-07","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-07","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3704,"dynamic_units":81,"fdr_alpha":0.01,"fixed":0.7556,"fixed_units":45,"gap":0.3852,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":3.4132765621506804e-05,"paired_depth":9},"key":["2026-10-07","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-08","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.3929,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.8857,"fixed_units":70,"gap":0.4929,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":3.7416703515657204e-10,"paired_depth":14},"key":["2026-10-08","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-08","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7698,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2302,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":1.3711517212922776e-05,"paired_depth":14},"key":["2026-10-08","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-08","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3778,"dynamic_units":90,"fdr_alpha":0.01,"fixed":0.76,"fixed_units":50,"gap":0.3822,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":1.4525559212016641e-05,"paired_depth":10},"key":["2026-10-08","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-09","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4048,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9,"fixed_units":70,"gap":0.4952,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":2.3304166604576286e-10,"paired_depth":14},"key":["2026-10-09","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-09","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3737,"dynamic_units":99,"fdr_alpha":0.01,"fixed":0.7636,"fixed_units":55,"gap":0.3899,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":3.5113421474667328e-06,"paired_depth":11},"key":["2026-10-09","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-09","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7778,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2222,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":2.0436806886962484e-05,"paired_depth":14},"key":["2026-10-09","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-10","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4048,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.8857,"fixed_units":70,"gap":0.481,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":8.601896744944855e-10,"paired_depth":14},"key":["2026-10-10","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-10","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3611,"dynamic_units":108,"fdr_alpha":0.01,"fixed":0.7667,"fixed_units":60,"gap":0.4056,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":4.708256002798286e-07,"paired_depth":12},"key":["2026-10-10","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-10","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7619,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2381,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":9.16161721353686e-06,"paired_depth":14},"key":["2026-10-10","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-11","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4167,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9143,"fixed_units":70,"gap":0.4976,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":1.387832920382488e-10,"paired_depth":14},"key":["2026-10-11","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-11","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3504,"dynamic_units":117,"fdr_alpha":0.01,"fixed":0.7692,"fixed_units":65,"gap":0.4188,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":6.147831419205027e-08,"paired_depth":13},"key":["2026-10-11","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-11","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7619,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2381,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":9.16161721353686e-06,"paired_depth":14},"key":["2026-10-11","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-12","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4167,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9286,"fixed_units":70,"gap":0.5119,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":3.3820298832419325e-11,"paired_depth":14},"key":["2026-10-12","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-12","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3492,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.7714,"fixed_units":70,"gap":0.4222,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":1.4727722527370795e-08,"paired_depth":14},"key":["2026-10-12","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-12","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7619,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2381,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":9.16161721353686e-06,"paired_depth":14},"key":["2026-10-12","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-13","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4286,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9143,"fixed_units":70,"gap":0.4857,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":3.179884119725757e-10,"paired_depth":14},"key":["2026-10-13","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-13","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3571,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.7714,"fixed_units":70,"gap":0.4143,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":2.7207878675458885e-08,"paired_depth":14},"key":["2026-10-13","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-13","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7619,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2381,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":9.16161721353686e-06,"paired_depth":14},"key":["2026-10-13","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-14","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4286,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9286,"fixed_units":70,"gap":0.5,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":7.86816586280802e-11,"paired_depth":14},"key":["2026-10-14","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-14","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3413,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.7714,"fixed_units":70,"gap":0.4302,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":7.857574426994563e-09,"paired_depth":14},"key":["2026-10-14","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-14","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.754,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.246,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":6.095702608804483e-06,"paired_depth":14},"key":["2026-10-14","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-15","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4286,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9286,"fixed_units":70,"gap":0.5,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":7.86816586280802e-11,"paired_depth":14},"key":["2026-10-15","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-15","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3333,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.7714,"fixed_units":70,"gap":0.4381,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":4.130297471520185e-09,"paired_depth":14},"key":["2026-10-15","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-15","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.754,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.246,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":6.095702608804483e-06,"paired_depth":14},"key":["2026-10-15","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-16","finding":{"comparisons":135,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4167,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9286,"fixed_units":70,"gap":0.5119,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":3.3820298832419325e-11,"paired_depth":14},"key":["2026-10-16","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-16","finding":{"comparisons":135,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3333,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.7714,"fixed_units":70,"gap":0.4381,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":4.130297471520185e-09,"paired_depth":14},"key":["2026-10-16","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-16","finding":{"comparisons":135,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7619,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2381,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":9.16161721353686e-06,"paired_depth":14},"key":["2026-10-16","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-17","finding":{"comparisons":136,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4048,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9429,"fixed_units":70,"gap":0.5381,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":3.213627796587065e-12,"paired_depth":14},"key":["2026-10-17","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-17","finding":{"comparisons":136,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3333,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.7857,"fixed_units":70,"gap":0.4524,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":1.281946032036226e-09,"paired_depth":14},"key":["2026-10-17","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-17","finding":{"comparisons":136,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7698,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2302,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":1.3711517212922776e-05,"paired_depth":14},"key":["2026-10-17","daily","mistral-large@mistral","capability"]},{"cadence":"weekly","date":"2026-10-18","finding":{"comparisons":64,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8095,"dynamic_units":63,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":168,"gap":0.1905,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":6.255881673880986e-09,"paired_depth":7},"key":["2026-10-18","weekly","mistral-large@mistral","capability"]},{"cadence":"weekly","date":"2026-10-18","finding":{"comparisons":64,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8095,"dynamic_units":63,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":168,"gap":0.1905,"level":"divergence","metric":"tier_gap","model":"sarvam-105b@sarvam","p":6.255881673880986e-09,"paired_depth":7},"key":["2026-10-18","weekly","sarvam-105b@sarvam","capability"]},{"cadence":"weekly","date":"2026-10-18","finding":{"comparisons":64,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7143,"dynamic_units":63,"fdr_alpha":0.01,"fixed":0.9464,"fixed_units":168,"gap":0.2321,"level":"divergence","metric":"tier_gap","model":"mistral-small@mistral","p":1.0037318638943735e-06,"paired_depth":7},"key":["2026-10-18","weekly","mistral-small@mistral","capability"]},{"cadence":"weekly","date":"2026-10-18","finding":{"comparisons":64,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.9048,"dynamic_units":63,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":168,"gap":0.0952,"level":"divergence","metric":"tier_gap","model":"deepseek-chat@deepseek","p":5.0568799250217334e-05,"paired_depth":7},"key":["2026-10-18","weekly","deepseek-chat@deepseek","capability"]},{"cadence":"weekly","date":"2026-10-18","finding":{"comparisons":64,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.9048,"dynamic_units":63,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":168,"gap":0.0952,"level":"divergence","metric":"tier_gap","model":"qwen3-235b@deepinfra","p":5.0568799250217334e-05,"paired_depth":7},"key":["2026-10-18","weekly","qwen3-235b@deepinfra","capability"]},{"cadence":"weekly","date":"2026-10-18","finding":{"comparisons":64,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8571,"dynamic_units":63,"fdr_alpha":0.01,"fixed":0.9762,"fixed_units":168,"gap":0.119,"level":"divergence","metric":"tier_gap","model":"llama-4-maverick@deepinfra","p":0.00047114617199675563,"paired_depth":7},"key":["2026-10-18","weekly","llama-4-maverick@deepinfra","capability"]},{"cadence":"daily","date":"2026-10-18","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4167,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9429,"fixed_units":70,"gap":0.5262,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":7.715288834501262e-12,"paired_depth":14},"key":["2026-10-18","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-18","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3571,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":70,"gap":0.4429,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":2.7757640189508327e-09,"paired_depth":14},"key":["2026-10-18","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-18","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7778,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2222,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":2.0436806886962484e-05,"paired_depth":14},"key":["2026-10-18","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-18","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.6667,"dynamic_units":42,"fdr_alpha":0.01,"fixed":0.9714,"fixed_units":35,"gap":0.3048,"level":"divergence","metric":"tier_gap","model":"gemini-3.1-pro-preview","p":0.0007732476602813601,"paired_depth":7},"key":["2026-10-18","daily","gemini-3.1-pro-preview","instruction-following"]},{"cadence":"daily","date":"2026-10-19","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4286,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9429,"fixed_units":70,"gap":0.5143,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":1.8206346981325876e-11,"paired_depth":14},"key":["2026-10-19","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-19","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.373,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":70,"gap":0.427,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":9.69021789991151e-09,"paired_depth":14},"key":["2026-10-19","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-19","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7698,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2302,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":1.3711517212922776e-05,"paired_depth":14},"key":["2026-10-19","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-19","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.6875,"dynamic_units":48,"fdr_alpha":0.01,"fixed":0.975,"fixed_units":40,"gap":0.2875,"level":"divergence","metric":"tier_gap","model":"gemini-3.1-pro-preview","p":0.0004980594259242371,"paired_depth":8},"key":["2026-10-19","daily","gemini-3.1-pro-preview","instruction-following"]},{"cadence":"daily","date":"2026-10-20","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4405,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9429,"fixed_units":70,"gap":0.5024,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":4.224923049718101e-11,"paired_depth":14},"key":["2026-10-20","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-20","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3651,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":70,"gap":0.4349,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":5.221986238264789e-09,"paired_depth":14},"key":["2026-10-20","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-20","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7619,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2381,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":9.16161721353686e-06,"paired_depth":14},"key":["2026-10-20","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-20","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.6852,"dynamic_units":54,"fdr_alpha":0.01,"fixed":0.9778,"fixed_units":45,"gap":0.2926,"level":"divergence","metric":"tier_gap","model":"gemini-3.1-pro-preview","p":0.00017098975687197915,"paired_depth":9},"key":["2026-10-20","daily","gemini-3.1-pro-preview","instruction-following"]},{"cadence":"daily","date":"2026-10-21","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4405,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9571,"fixed_units":70,"gap":0.5167,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":9.230859303196678e-12,"paired_depth":14},"key":["2026-10-21","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-21","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3651,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":70,"gap":0.4349,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":5.221986238264789e-09,"paired_depth":14},"key":["2026-10-21","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-21","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.746,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.254,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":4.038234218531066e-06,"paired_depth":14},"key":["2026-10-21","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-21","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.6833,"dynamic_units":60,"fdr_alpha":0.01,"fixed":0.96,"fixed_units":50,"gap":0.2767,"level":"divergence","metric":"tier_gap","model":"gemini-3.1-pro-preview","p":0.0002366552475989579,"paired_depth":10},"key":["2026-10-21","daily","gemini-3.1-pro-preview","instruction-following"]},{"cadence":"daily","date":"2026-10-22","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4286,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9714,"fixed_units":70,"gap":0.5429,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":7.857053846615167e-13,"paired_depth":14},"key":["2026-10-22","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-22","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3571,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":70,"gap":0.4429,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":2.7757640189508327e-09,"paired_depth":14},"key":["2026-10-22","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-22","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.754,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.246,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":6.095702608804483e-06,"paired_depth":14},"key":["2026-10-22","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-22","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.6818,"dynamic_units":66,"fdr_alpha":0.01,"fixed":0.9455,"fixed_units":55,"gap":0.2636,"level":"divergence","metric":"tier_gap","model":"gemini-3.1-pro-preview","p":0.00029317061181311654,"paired_depth":11},"key":["2026-10-22","daily","gemini-3.1-pro-preview","instruction-following"]},{"cadence":"daily","date":"2026-10-23","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4286,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9714,"fixed_units":70,"gap":0.5429,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":7.857053846615167e-13,"paired_depth":14},"key":["2026-10-23","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-23","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3651,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":70,"gap":0.4349,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":5.221986238264789e-09,"paired_depth":14},"key":["2026-10-23","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-23","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7619,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2381,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":9.16161721353686e-06,"paired_depth":14},"key":["2026-10-23","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-23","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.6806,"dynamic_units":72,"fdr_alpha":0.01,"fixed":0.95,"fixed_units":60,"gap":0.2694,"level":"divergence","metric":"tier_gap","model":"gemini-3.1-pro-preview","p":0.00010628621969487462,"paired_depth":12},"key":["2026-10-23","daily","gemini-3.1-pro-preview","instruction-following"]},{"cadence":"daily","date":"2026-10-24","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4286,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9714,"fixed_units":70,"gap":0.5429,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":7.857053846615167e-13,"paired_depth":14},"key":["2026-10-24","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-24","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.373,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":70,"gap":0.427,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":9.69021789991151e-09,"paired_depth":14},"key":["2026-10-24","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-24","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7778,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2222,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":2.0436806886962484e-05,"paired_depth":14},"key":["2026-10-24","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-24","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.6923,"dynamic_units":78,"fdr_alpha":0.01,"fixed":0.9538,"fixed_units":65,"gap":0.2615,"level":"divergence","metric":"tier_gap","model":"gemini-3.1-pro-preview","p":6.914510644889256e-05,"paired_depth":13},"key":["2026-10-24","daily","gemini-3.1-pro-preview","instruction-following"]},{"cadence":"weekly","date":"2026-10-25","finding":{"comparisons":84,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7937,"dynamic_units":63,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":168,"gap":0.2063,"level":"divergence","metric":"tier_gap","model":"claude-fable-5.1","p":1.3540113095929347e-09,"paired_depth":7},"key":["2026-10-25","weekly","claude-fable-5.1","capability"]},{"cadence":"weekly","date":"2026-10-25","finding":{"comparisons":84,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8194,"dynamic_units":72,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":192,"gap":0.1806,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":1.5565967466426633e-09,"paired_depth":8},"key":["2026-10-25","weekly","mistral-large@mistral","capability"]},{"cadence":"weekly","date":"2026-10-25","finding":{"comparisons":84,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8194,"dynamic_units":72,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":192,"gap":0.1806,"level":"divergence","metric":"tier_gap","model":"sarvam-105b@sarvam","p":1.5565967466426633e-09,"paired_depth":8},"key":["2026-10-25","weekly","sarvam-105b@sarvam","capability"]},{"cadence":"weekly","date":"2026-10-25","finding":{"comparisons":84,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8413,"dynamic_units":63,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":168,"gap":0.1587,"level":"divergence","metric":"tier_gap","model":"claude-fable-5","p":1.2952463366641033e-07,"paired_depth":7},"key":["2026-10-25","weekly","claude-fable-5","capability"]},{"cadence":"weekly","date":"2026-10-25","finding":{"comparisons":84,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7222,"dynamic_units":72,"fdr_alpha":0.01,"fixed":0.9479,"fixed_units":192,"gap":0.2257,"level":"divergence","metric":"tier_gap","model":"mistral-small@mistral","p":2.66076626772105e-07,"paired_depth":8},"key":["2026-10-25","weekly","mistral-small@mistral","capability"]},{"cadence":"weekly","date":"2026-10-25","finding":{"comparisons":84,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8889,"dynamic_units":72,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":192,"gap":0.1111,"level":"divergence","metric":"tier_gap","model":"qwen3-235b@deepinfra","p":2.726504656155448e-06,"paired_depth":8},"key":["2026-10-25","weekly","qwen3-235b@deepinfra","capability"]},{"cadence":"weekly","date":"2026-10-25","finding":{"comparisons":84,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.9028,"dynamic_units":72,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":192,"gap":0.0972,"level":"divergence","metric":"tier_gap","model":"deepseek-chat@deepseek","p":1.1925909751089332e-05,"paired_depth":8},"key":["2026-10-25","weekly","deepseek-chat@deepseek","capability"]},{"cadence":"weekly","date":"2026-10-25","finding":{"comparisons":84,"correction":"benjamini-hochberg","dimension":"tool-call","dynamic":0.7619,"dynamic_units":21,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2381,"level":"divergence","metric":"tier_gap","model":"claude-fable-5","p":2.6752491019261747e-05,"paired_depth":7},"key":["2026-10-25","weekly","claude-fable-5","tool-call"]},{"cadence":"weekly","date":"2026-10-25","finding":{"comparisons":84,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8889,"dynamic_units":72,"fdr_alpha":0.01,"fixed":0.9896,"fixed_units":192,"gap":0.1007,"level":"divergence","metric":"tier_gap","model":"gpt-5","p":0.00013515480870757325,"paired_depth":8},"key":["2026-10-25","weekly","gpt-5","capability"]},{"cadence":"weekly","date":"2026-10-25","finding":{"comparisons":84,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.875,"dynamic_units":72,"fdr_alpha":0.01,"fixed":0.9792,"fixed_units":192,"gap":0.1042,"level":"divergence","metric":"tier_gap","model":"llama-4-maverick@deepinfra","p":0.000494558558422653,"paired_depth":8},"key":["2026-10-25","weekly","llama-4-maverick@deepinfra","capability"]},{"cadence":"weekly","date":"2026-10-25","finding":{"comparisons":84,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.8125,"dynamic_units":48,"fdr_alpha":0.01,"fixed":0.9609,"fixed_units":128,"gap":0.1484,"level":"divergence","metric":"tier_gap","model":"sarvam-105b@sarvam","p":0.001190332112584942,"paired_depth":8},"key":["2026-10-25","weekly","sarvam-105b@sarvam","instruction-following"]},{"cadence":"daily","date":"2026-10-25","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4167,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9714,"fixed_units":70,"gap":0.5548,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":3.247907171750042e-13,"paired_depth":14},"key":["2026-10-25","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-25","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3889,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":70,"gap":0.4111,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":3.20671188668547e-08,"paired_depth":14},"key":["2026-10-25","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-25","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7698,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2302,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":1.3711517212922776e-05,"paired_depth":14},"key":["2026-10-25","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-25","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.6905,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9571,"fixed_units":70,"gap":0.2667,"level":"divergence","metric":"tier_gap","model":"gemini-3.1-pro-preview","p":2.5014179877737818e-05,"paired_depth":14},"key":["2026-10-25","daily","gemini-3.1-pro-preview","instruction-following"]},{"cadence":"daily","date":"2026-10-25","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8571,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.1429,"level":"divergence","metric":"tier_gap","model":"deepseek-chat@deepseek","p":0.0009056123985935735,"paired_depth":14},"key":["2026-10-25","daily","deepseek-chat@deepseek","capability"]},{"cadence":"daily","date":"2026-10-26","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4286,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9714,"fixed_units":70,"gap":0.5429,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":7.857053846615167e-13,"paired_depth":14},"key":["2026-10-26","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-26","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3889,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":70,"gap":0.4111,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":3.20671188668547e-08,"paired_depth":14},"key":["2026-10-26","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-26","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7698,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2302,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":1.3711517212922776e-05,"paired_depth":14},"key":["2026-10-26","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-26","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.6905,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9429,"fixed_units":70,"gap":0.2524,"level":"divergence","metric":"tier_gap","model":"gemini-3.1-pro-preview","p":8.229276637657561e-05,"paired_depth":14},"key":["2026-10-26","daily","gemini-3.1-pro-preview","instruction-following"]},{"cadence":"daily","date":"2026-10-26","finding":{"comparisons":148,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8651,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.1349,"level":"divergence","metric":"tier_gap","model":"deepseek-chat@deepseek","p":0.0013007911271812748,"paired_depth":14},"key":["2026-10-26","daily","deepseek-chat@deepseek","capability"]},{"cadence":"daily","date":"2026-10-27","finding":{"comparisons":166,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4167,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9857,"fixed_units":70,"gap":0.569,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":5.947178614647148e-14,"paired_depth":14},"key":["2026-10-27","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-27","finding":{"comparisons":166,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3968,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":70,"gap":0.4032,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":5.7223012468198844e-08,"paired_depth":14},"key":["2026-10-27","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-27","finding":{"comparisons":166,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7619,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2381,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":9.16161721353686e-06,"paired_depth":14},"key":["2026-10-27","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-27","finding":{"comparisons":166,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.6905,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9286,"fixed_units":70,"gap":0.2381,"level":"divergence","metric":"tier_gap","model":"gemini-3.1-pro-preview","p":0.0002433513194769493,"paired_depth":14},"key":["2026-10-27","daily","gemini-3.1-pro-preview","instruction-following"]},{"cadence":"daily","date":"2026-10-27","finding":{"comparisons":166,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8651,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.1349,"level":"divergence","metric":"tier_gap","model":"deepseek-chat@deepseek","p":0.0013007911271812748,"paired_depth":14},"key":["2026-10-27","daily","deepseek-chat@deepseek","capability"]},{"cadence":"daily","date":"2026-10-28","finding":{"comparisons":168,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4048,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9857,"fixed_units":70,"gap":0.581,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":2.3923109478224655e-14,"paired_depth":14},"key":["2026-10-28","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-28","finding":{"comparisons":168,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3968,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":70,"gap":0.4032,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":5.7223012468198844e-08,"paired_depth":14},"key":["2026-10-28","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-28","finding":{"comparisons":168,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7698,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2302,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":1.3711517212922776e-05,"paired_depth":14},"key":["2026-10-28","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-28","finding":{"comparisons":168,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.7024,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9286,"fixed_units":70,"gap":0.2262,"level":"divergence","metric":"tier_gap","model":"gemini-3.1-pro-preview","p":0.000417130440200363,"paired_depth":14},"key":["2026-10-28","daily","gemini-3.1-pro-preview","instruction-following"]},{"cadence":"daily","date":"2026-10-28","finding":{"comparisons":168,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8651,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.1349,"level":"divergence","metric":"tier_gap","model":"deepseek-chat@deepseek","p":0.0013007911271812748,"paired_depth":14},"key":["2026-10-28","daily","deepseek-chat@deepseek","capability"]},{"cadence":"daily","date":"2026-10-29","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4048,"dynamic_units":84,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.5952,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":4.002408219234416e-15,"paired_depth":14},"key":["2026-10-29","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-29","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3968,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":70,"gap":0.4032,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":5.7223012468198844e-08,"paired_depth":14},"key":["2026-10-29","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-29","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7698,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2302,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":1.3711517212922776e-05,"paired_depth":14},"key":["2026-10-29","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-29","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8571,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.1429,"level":"divergence","metric":"tier_gap","model":"deepseek-chat@deepseek","p":0.0009056123985935735,"paired_depth":14},"key":["2026-10-29","daily","deepseek-chat@deepseek","capability"]},{"cadence":"daily","date":"2026-10-29","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.7024,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9143,"fixed_units":70,"gap":0.2119,"level":"divergence","metric":"tier_gap","model":"gemini-3.1-pro-preview","p":0.001092517178041438,"paired_depth":14},"key":["2026-10-29","daily","gemini-3.1-pro-preview","instruction-following"]},{"cadence":"daily","date":"2026-10-30","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4286,"dynamic_units":84,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.5714,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":2.474593231105502e-14,"paired_depth":14},"key":["2026-10-30","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-30","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3968,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":70,"gap":0.4032,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":5.7223012468198844e-08,"paired_depth":14},"key":["2026-10-30","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-30","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7698,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2302,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":1.3711517212922776e-05,"paired_depth":14},"key":["2026-10-30","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-30","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8492,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.1508,"level":"divergence","metric":"tier_gap","model":"deepseek-chat@deepseek","p":0.0006288291995916783,"paired_depth":14},"key":["2026-10-30","daily","deepseek-chat@deepseek","capability"]},{"cadence":"daily","date":"2026-10-30","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.7051,"dynamic_units":78,"fdr_alpha":0.01,"fixed":0.9231,"fixed_units":65,"gap":0.2179,"level":"divergence","metric":"tier_gap","model":"gemini-3.1-pro-preview","p":0.0010740263381892148,"paired_depth":13},"key":["2026-10-30","daily","gemini-3.1-pro-preview","instruction-following"]},{"cadence":"daily","date":"2026-10-31","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4405,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9857,"fixed_units":70,"gap":0.5452,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":3.4949996774659877e-13,"paired_depth":14},"key":["2026-10-31","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-10-31","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.4048,"dynamic_units":126,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":70,"gap":0.3952,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":1.0085351624701961e-07,"paired_depth":14},"key":["2026-10-31","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-10-31","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7698,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2302,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":1.3711517212922776e-05,"paired_depth":14},"key":["2026-10-31","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-10-31","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8571,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.1429,"level":"divergence","metric":"tier_gap","model":"deepseek-chat@deepseek","p":0.0009056123985935735,"paired_depth":14},"key":["2026-10-31","daily","deepseek-chat@deepseek","capability"]},{"cadence":"weekly","date":"2026-11-01","finding":{"comparisons":100,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8148,"dynamic_units":81,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":216,"gap":0.1852,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":8.550519788721827e-11,"paired_depth":9},"key":["2026-11-01","weekly","mistral-large@mistral","capability"]},{"cadence":"weekly","date":"2026-11-01","finding":{"comparisons":100,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8148,"dynamic_units":81,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":216,"gap":0.1852,"level":"divergence","metric":"tier_gap","model":"sarvam-105b@sarvam","p":8.550519788721827e-11,"paired_depth":9},"key":["2026-11-01","weekly","sarvam-105b@sarvam","capability"]},{"cadence":"weekly","date":"2026-11-01","finding":{"comparisons":100,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7937,"dynamic_units":63,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":168,"gap":0.2063,"level":"divergence","metric":"tier_gap","model":"claude-fable-5.1","p":1.3540113095929347e-09,"paired_depth":7},"key":["2026-11-01","weekly","claude-fable-5.1","capability"]},{"cadence":"weekly","date":"2026-11-01","finding":{"comparisons":100,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8413,"dynamic_units":63,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":168,"gap":0.1587,"level":"divergence","metric":"tier_gap","model":"claude-fable-5","p":1.2952463366641033e-07,"paired_depth":7},"key":["2026-11-01","weekly","claude-fable-5","capability"]},{"cadence":"weekly","date":"2026-11-01","finding":{"comparisons":100,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7407,"dynamic_units":81,"fdr_alpha":0.01,"fixed":0.9491,"fixed_units":216,"gap":0.2083,"level":"divergence","metric":"tier_gap","model":"mistral-small@mistral","p":2.507578750193655e-07,"paired_depth":9},"key":["2026-11-01","weekly","mistral-small@mistral","capability"]},{"cadence":"weekly","date":"2026-11-01","finding":{"comparisons":100,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8889,"dynamic_units":81,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":216,"gap":0.1111,"level":"divergence","metric":"tier_gap","model":"qwen3-235b@deepinfra","p":6.526880098391003e-07,"paired_depth":9},"key":["2026-11-01","weekly","qwen3-235b@deepinfra","capability"]},{"cadence":"weekly","date":"2026-11-01","finding":{"comparisons":100,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.9136,"dynamic_units":81,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":216,"gap":0.0864,"level":"divergence","metric":"tier_gap","model":"deepseek-chat@deepseek","p":1.2292934840558571e-05,"paired_depth":9},"key":["2026-11-01","weekly","deepseek-chat@deepseek","capability"]},{"cadence":"weekly","date":"2026-11-01","finding":{"comparisons":100,"correction":"benjamini-hochberg","dimension":"tool-call","dynamic":0.7619,"dynamic_units":21,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2381,"level":"divergence","metric":"tier_gap","model":"claude-fable-5","p":2.6752491019261747e-05,"paired_depth":7},"key":["2026-11-01","weekly","claude-fable-5","tool-call"]},{"cadence":"weekly","date":"2026-11-01","finding":{"comparisons":100,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8889,"dynamic_units":81,"fdr_alpha":0.01,"fixed":0.9907,"fixed_units":216,"gap":0.1019,"level":"divergence","metric":"tier_gap","model":"gpt-5","p":3.482184571228073e-05,"paired_depth":9},"key":["2026-11-01","weekly","gpt-5","capability"]},{"cadence":"weekly","date":"2026-11-01","finding":{"comparisons":100,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8765,"dynamic_units":81,"fdr_alpha":0.01,"fixed":0.9815,"fixed_units":216,"gap":0.1049,"level":"divergence","metric":"tier_gap","model":"llama-4-maverick@deepinfra","p":0.00014448836391046601,"paired_depth":9},"key":["2026-11-01","weekly","llama-4-maverick@deepinfra","capability"]},{"cadence":"weekly","date":"2026-11-01","finding":{"comparisons":100,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.9506,"dynamic_units":81,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":216,"gap":0.0494,"level":"divergence","metric":"tier_gap","model":"gpt-5.6-terra","p":0.0010082868719564768,"paired_depth":9},"key":["2026-11-01","weekly","gpt-5.6-terra","capability"]},{"cadence":"weekly","date":"2026-11-01","finding":{"comparisons":100,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.8333,"dynamic_units":54,"fdr_alpha":0.01,"fixed":0.9653,"fixed_units":144,"gap":0.1319,"level":"divergence","metric":"tier_gap","model":"sarvam-105b@sarvam","p":0.0012564893837419557,"paired_depth":9},"key":["2026-11-01","weekly","sarvam-105b@sarvam","instruction-following"]},{"cadence":"daily","date":"2026-11-01","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4405,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9714,"fixed_units":70,"gap":0.531,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":1.8696009105450997e-12,"paired_depth":14},"key":["2026-11-01","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-11-01","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3846,"dynamic_units":117,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":65,"gap":0.4154,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":7.36795707601351e-08,"paired_depth":13},"key":["2026-11-01","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-11-01","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7619,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2381,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":9.16161721353686e-06,"paired_depth":14},"key":["2026-11-01","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-11-02","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4286,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9571,"fixed_units":70,"gap":0.5286,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":3.925642860330132e-12,"paired_depth":14},"key":["2026-11-02","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-11-02","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3796,"dynamic_units":108,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":60,"gap":0.4204,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":1.6880468086989552e-07,"paired_depth":12},"key":["2026-11-02","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-11-02","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7698,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2302,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":1.3711517212922776e-05,"paired_depth":14},"key":["2026-11-02","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-11-03","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4231,"dynamic_units":78,"fdr_alpha":0.01,"fixed":0.9538,"fixed_units":65,"gap":0.5308,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":2.1922951628692748e-11,"paired_depth":13},"key":["2026-11-03","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-11-03","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3939,"dynamic_units":99,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":55,"gap":0.4061,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":1.2740965121426203e-06,"paired_depth":11},"key":["2026-11-03","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-11-03","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7778,"dynamic_units":117,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":65,"gap":0.2222,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":4.041387736263971e-05,"paired_depth":13},"key":["2026-11-03","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-11-04","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4405,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9571,"fixed_units":70,"gap":0.5167,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":9.230859303196678e-12,"paired_depth":14},"key":["2026-11-04","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-11-04","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3889,"dynamic_units":108,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":60,"gap":0.4111,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":3.062461648257195e-07,"paired_depth":12},"key":["2026-11-04","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-11-04","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7937,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2063,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":4.486520279556613e-05,"paired_depth":14},"key":["2026-11-04","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-11-05","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4524,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9571,"fixed_units":70,"gap":0.5048,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":2.135823419404534e-11,"paired_depth":14},"key":["2026-11-05","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-11-05","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3889,"dynamic_units":108,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":60,"gap":0.4111,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":3.062461648257195e-07,"paired_depth":12},"key":["2026-11-05","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-11-05","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8016,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.1984,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":6.609675098150712e-05,"paired_depth":14},"key":["2026-11-05","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-11-06","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4524,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9571,"fixed_units":70,"gap":0.5048,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":2.135823419404534e-11,"paired_depth":14},"key":["2026-11-06","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-11-06","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3889,"dynamic_units":108,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":60,"gap":0.4111,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":3.062461648257195e-07,"paired_depth":12},"key":["2026-11-06","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-11-06","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7937,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2063,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":4.486520279556614e-05,"paired_depth":14},"key":["2026-11-06","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-11-07","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4524,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9429,"fixed_units":70,"gap":0.4905,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":9.645900194118998e-11,"paired_depth":14},"key":["2026-11-07","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-11-07","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3981,"dynamic_units":108,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":60,"gap":0.4019,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":5.474299654266831e-07,"paired_depth":12},"key":["2026-11-07","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-11-07","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7937,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.2063,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":4.486520279556614e-05,"paired_depth":14},"key":["2026-11-07","daily","mistral-large@mistral","capability"]},{"cadence":"weekly","date":"2026-11-08","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.5397,"dynamic_units":63,"fdr_alpha":0.01,"fixed":0.9464,"fixed_units":168,"gap":0.4067,"level":"divergence","metric":"tier_gap","model":"deepseek-v4-flash-0731@deepinfra","p":1.1151477662060912e-13,"paired_depth":7},"key":["2026-11-08","weekly","deepseek-v4-flash-0731@deepinfra","capability"]},{"cadence":"weekly","date":"2026-11-08","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8,"dynamic_units":90,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":240,"gap":0.2,"level":"divergence","metric":"tier_gap","model":"sarvam-105b@sarvam","p":1.0388965492545747e-12,"paired_depth":10},"key":["2026-11-08","weekly","sarvam-105b@sarvam","capability"]},{"cadence":"weekly","date":"2026-11-08","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8111,"dynamic_units":90,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":240,"gap":0.1889,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":4.730700819032354e-12,"paired_depth":10},"key":["2026-11-08","weekly","mistral-large@mistral","capability"]},{"cadence":"weekly","date":"2026-11-08","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7917,"dynamic_units":72,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":192,"gap":0.2083,"level":"divergence","metric":"tier_gap","model":"claude-fable-5.1","p":7.402433956432056e-11,"paired_depth":8},"key":["2026-11-08","weekly","claude-fable-5.1","capability"]},{"cadence":"weekly","date":"2026-11-08","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8333,"dynamic_units":72,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":192,"gap":0.1667,"level":"divergence","metric":"tier_gap","model":"claude-fable-5","p":7.039693686866462e-09,"paired_depth":8},"key":["2026-11-08","weekly","claude-fable-5","capability"]},{"cadence":"weekly","date":"2026-11-08","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.7444,"dynamic_units":90,"fdr_alpha":0.01,"fixed":0.95,"fixed_units":240,"gap":0.2056,"level":"divergence","metric":"tier_gap","model":"mistral-small@mistral","p":6.629865745003493e-08,"paired_depth":10},"key":["2026-11-08","weekly","mistral-small@mistral","capability"]},{"cadence":"weekly","date":"2026-11-08","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8889,"dynamic_units":90,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":240,"gap":0.1111,"level":"divergence","metric":"tier_gap","model":"qwen3-235b@deepinfra","p":1.5709450561557817e-07,"paired_depth":10},"key":["2026-11-08","weekly","qwen3-235b@deepinfra","capability"]},{"cadence":"weekly","date":"2026-11-08","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.9111,"dynamic_units":90,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":240,"gap":0.0889,"level":"divergence","metric":"tier_gap","model":"deepseek-chat@deepseek","p":2.927719720885413e-06,"paired_depth":10},"key":["2026-11-08","weekly","deepseek-chat@deepseek","capability"]},{"cadence":"weekly","date":"2026-11-08","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8889,"dynamic_units":90,"fdr_alpha":0.01,"fixed":0.9917,"fixed_units":240,"gap":0.1028,"level":"divergence","metric":"tier_gap","model":"gpt-5","p":8.912515504367887e-06,"paired_depth":10},"key":["2026-11-08","weekly","gpt-5","capability"]},{"cadence":"weekly","date":"2026-11-08","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"tool-call","dynamic":0.7917,"dynamic_units":24,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":80,"gap":0.2083,"level":"divergence","metric":"tier_gap","model":"claude-fable-5","p":2.8603847837561514e-05,"paired_depth":8},"key":["2026-11-08","weekly","claude-fable-5","tool-call"]},{"cadence":"weekly","date":"2026-11-08","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8889,"dynamic_units":90,"fdr_alpha":0.01,"fixed":0.9833,"fixed_units":240,"gap":0.0944,"level":"divergence","metric":"tier_gap","model":"llama-4-maverick@deepinfra","p":0.00015004765964046486,"paired_depth":10},"key":["2026-11-08","weekly","llama-4-maverick@deepinfra","capability"]},{"cadence":"weekly","date":"2026-11-08","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.8333,"dynamic_units":60,"fdr_alpha":0.01,"fixed":0.9688,"fixed_units":160,"gap":0.1354,"level":"divergence","metric":"tier_gap","model":"sarvam-105b@sarvam","p":0.00038681089957780777,"paired_depth":10},"key":["2026-11-08","weekly","sarvam-105b@sarvam","instruction-following"]},{"cadence":"weekly","date":"2026-11-08","finding":{"comparisons":124,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.9556,"dynamic_units":90,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":240,"gap":0.0444,"level":"divergence","metric":"tier_gap","model":"gpt-5.6-terra","p":0.0010163473390919265,"paired_depth":10},"key":["2026-11-08","weekly","gpt-5.6-terra","capability"]},{"cadence":"daily","date":"2026-11-08","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4524,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9429,"fixed_units":70,"gap":0.4905,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":9.645900194118998e-11,"paired_depth":14},"key":["2026-11-08","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-11-08","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3889,"dynamic_units":108,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":60,"gap":0.4111,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":3.062461648257195e-07,"paired_depth":12},"key":["2026-11-08","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-11-08","finding":{"comparisons":164,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8016,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.1984,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":6.609675098150712e-05,"paired_depth":14},"key":["2026-11-08","daily","mistral-large@mistral","capability"]},{"cadence":"daily","date":"2026-11-09","finding":{"comparisons":172,"correction":"benjamini-hochberg","dimension":"instruction-following","dynamic":0.4524,"dynamic_units":84,"fdr_alpha":0.01,"fixed":0.9429,"fixed_units":70,"gap":0.4905,"level":"divergence","metric":"tier_gap","model":"grok-4.7@xai","p":9.645900194118998e-11,"paired_depth":14},"key":["2026-11-09","daily","grok-4.7@xai","instruction-following"]},{"cadence":"daily","date":"2026-11-09","finding":{"comparisons":172,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.3889,"dynamic_units":108,"fdr_alpha":0.01,"fixed":0.8,"fixed_units":60,"gap":0.4111,"level":"divergence","metric":"tier_gap","model":"claude-sonnet-5-5","p":3.062461648257195e-07,"paired_depth":12},"key":["2026-11-09","daily","claude-sonnet-5-5","capability"]},{"cadence":"daily","date":"2026-11-09","finding":{"comparisons":172,"correction":"benjamini-hochberg","dimension":"capability","dynamic":0.8095,"dynamic_units":126,"fdr_alpha":0.01,"fixed":1.0,"fixed_units":70,"gap":0.1905,"level":"divergence","metric":"tier_gap","model":"mistral-large@mistral","p":9.702152402780321e-05,"paired_depth":14},"key":["2026-11-09","daily","mistral-large@mistral","capability"]}]}
