CSV
results.csv
16,615 bytes
SHA-256 c5542c033fe42b80…
case_key,case_sha256,status,error_present,deterministic_success,deterministic_quality,lexical_f1,required_term_rate,latency_ms,ttft_ms,tokens_per_second,gpu_energy_wh,prompt_tokens,output_tokens,total_tokens,llm_calls,rag_used,rag_cards_injected,escalated,web_used,memory_used,planner_used,review_used,response_trust,retrieval_hit,routing_match,judge_score,judge_support_score,judge_task_success,model_id,response_source,answer_sha256
tk-1,66c5f8b4bade4891aca75720f2092a5b4ac2adbbfb54c4cfcdbe612f821ac07e,complete,false,true,82.5,0.5,1,1459,442,74.879,0.031982,739,62,801,1,true,3,false,false,false,false,false,0.689,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,ad56dfc898c8bb5ff2baad976ec9c1d7555b8a76612aa4377105a145a39ff4bc
tk-12,e3be9dd3ac2c71731e64b5e16a594913da9dc4ab15b6c7493451baff74f222eb,complete,false,true,100,1,1,2383,212,75.117,0.13616,912,144,1056,1,true,2,false,false,false,false,false,0.688,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,664ec3d5c1237ff79d14ba0a922ab8b5d0a733204b583931bbed1085737eb708
tk-47,2e257dd23f55cfb7704685463a8aae17a3836de7385554c4dc671b555c5ee53a,complete,false,true,100,1,1,2109,89,77.558,0.120946,468,141,609,1,true,1,false,false,false,false,false,0.712,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,5578b459b96edf4850e40fd69f561e4a31510bdaebb9e979d16a62be6a68cb88
tk-63,b3d4cb5fc938c428ce50899bd754e1a546d35ae547a4b7b2d40e3435b3cd4b42,complete,false,true,78.5172,0.386207,1,2403,166,77.381,0.150364,776,169,945,1,true,2,false,false,false,false,false,0.681,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,0a2c3736afeb2e285f37f2d52d90ed6df114e88e6239e16003a1ce9ce6a37311
tk-49,7583adf568a2514239083a5915d3164b3ffcb5f48031ba4c8132680094189255,complete,false,true,100,1,1,2571,194,77.154,0.1642,842,180,1022,1,true,3,false,false,false,false,false,0.687,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,b21d49df633ffa7284e3f06175b4a7b03621d3e8f0f60de7a5ee2e8d45e9cfa2
tk-27,66a46427a4d0a3ecb01ac0bdc3e97f18fbea0ff49907087dda949345b092cfee,complete,false,true,89.6667,0.704762,1,2331,158,76.724,0.138049,689,148,837,1,true,2,false,false,false,false,false,0.702,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,4e0d9be4d340fa84605a235a9f99a9b865f0925e5a8aa4105cb64e4cf8054195
tk-40,2288a4bb044fb3b701a69544a482f7e1002eebc621dd5d4f1d91825d50c1078b,complete,false,true,87.9851,0.656716,1,3114,284,76.888,0.177808,1124,169,1293,1,true,3,false,false,false,false,false,0.688,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,0feac89d0eb939d8933cf679dd4fbf0bd8279b79bc7e41aca186dd2a02e129dd
tk-25,cc9f218b06268a3eabdc845af2eb51b775c1a38d153825dc610b6a21ae6c0417,complete,false,true,91.1111,0.746032,1,2701,269,71.658,0.145489,1005,134,1139,1,true,3,false,false,false,false,false,0.682,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,92e37e4cb35409f1fadba35e60b246d52817ffc66508abb1414259d972028484
tk-43,818fc8a8d5fd531139a673e3209773c807661ab1e895e02b8f94f07aff602866,complete,false,true,100,1,1,1921,235,65.44,0.097531,447,96,543,1,true,1,false,false,false,false,false,0.711,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,8ddb6884c45ad407d031ded6435814c84c02e594d32ccdbb45c14670dfb9347f
tk-21,4d5e8f409bcb4584f80fad9f04cef4dc51a63aaa5e14b9bc446c3cfb5672b99c,complete,false,true,67.8953,0.547009,0.75,1398,98,64.782,0.063671,511,55,566,1,true,1,false,false,false,false,false,0.712,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,366ce7bec0a20c83508d6580bc2076a6d21d4a0bf9b7b4125079cb31dc43de41
tk-23,a9b69596e031161a818c30b6a5a13417c1b09b54371c61c0b385aa6900eeeae2,complete,false,true,80.9914,0.456897,1,5474,694,69.622,0.33125,1922,289,2211,1,true,3,false,false,false,false,false,0.672,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,932e6dc75fad85bf78797df826b6c8d5e5c614b7e312be27ce568e4a6279831a
tk-52,ebfd89937dec5bd9b6d5a4275135340d904c2af6de4a69d9543a402aee9ffcfc,complete,false,true,100,1,1,1201,117,71.966,0.060458,448,67,515,1,true,1,false,false,false,false,false,0.701,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,2af0e22e03150a03965520057753b87cd3e94c3d9038071666fb3286cf729b08
tk-16,a566c4e378a815ef2fd5f6615201a2fe5de0f723f4bb6be875ee28dbc6592a8e,complete,false,true,93,0.8,1,1821,92,67.766,0.103761,494,111,605,1,true,1,false,false,false,false,false,0.701,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,ff83dcb35f4b032c1e336982b65b12ddfe467d8de0275c6db6db2a761dc3bed9
tk-60,d6f357db1b04f886dc212a828b46b93bc3a8bc71580ae0aeb87eb52540f93423,complete,false,true,89.7788,0.707965,1,1299,112,65.905,0.071561,503,75,578,1,true,1,false,false,false,false,false,0.699,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,2a737f34ed452b5495d1990547d929bd0321562b60e58271264ec617bf7bb153
tk-75,2757a3e04643f9f2e99dd684ed68bab373626bf52eccf20013d77a4bc14547c5,complete,false,false,9.2917,0.033333,0.125,1397,69,66.777,0.074411,420,81,501,1,true,1,false,false,false,false,false,0.697,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,19e9f067818020aedaf4e7479dc55f8abc26e572191df55d401ea5142c60e1f8
tk-31,73574819390bbd0f4a9469b7d1614193657237fdaae5ab41b49d96a80e80700b,complete,false,true,95.3333,0.866667,1,2276,171,68.892,0.131847,747,130,877,1,true,2,false,false,false,false,false,0.673,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,faa53e06266a9262b8749f8e785684aee9f642cf7feaff40067e813d0009bed1
tk-37,bc27d22cd2482426a4da2f972c91fbcab88eb6a8204300fa029d1cf3bba43b1b,complete,false,true,91.6418,0.761194,1,3000,254,69.066,0.163674,946,142,1088,1,true,2,false,false,false,false,false,0.682,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,244b2c4cc0f8f62ed14f0c38e9171e63b7dfe7ba51643ea2a831afe006e737c3
tk-4,de4812e55d86a70b2ffdf926dc5c6330dfadb4aa0043eb0a88c14098dd90d32b,complete,false,true,71.2924,0.644068,0.75,3137,141,68.571,0.183287,603,180,783,1,true,1,false,false,false,false,false,0.703,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,1256e672871d29febc00a418a0cef5ac00f455282616a263af59b5e3f65aa02d
tk-67,d2fd2b936280449894e4aebd2da84b9b43b411ddd6f824af767056b3931454a1,complete,false,true,79.0972,0.634921,0.875,2047,189,71.268,0.12278,716,127,843,1,true,3,false,false,false,false,false,0.684,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,ee394326773d5ee30e4856b898d3022086c667cb6354f1866e8c02008e30f8de
tk-7,94bc4ad1b1de70238dc5ab1ab2ed4887be42d5a1876a445dd50d483d2a885801,complete,false,true,77.0763,0.577181,0.875,2119,123,72.052,0.126296,539,132,671,1,true,1,false,false,false,false,false,0.704,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,26c68879da0ead1c6da2c364881409d36b9712d8d05510b4f20d87f5c747d28c
tk-17,1490f637d8dfe6389c77295501049439b59281ade10a05ce9097ec26a7531816,complete,false,true,100,1,1,1788,221,71.669,0.094407,901,85,986,1,true,3,false,false,false,false,false,0.672,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,8a0e2b971cdef39229908a5b4cd4fc5fb1ffb0139dc36cb5c9c952771235bd3b
tk-19,b8664336bb643d730cb10bcbf062f3715a0a1f3da361c1da474e7ea4af7323d5,complete,false,true,100,1,1,1713,91,71.655,0.103252,444,113,557,1,true,1,false,false,false,false,false,0.707,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,65af0f24bbdf568d15d4071b6afb53fdb1fc623d9956b30b11e152f312c4159b
tk-50,c2476b62438a5661ac49b801defd0f60714676d2cb96e33cd2bf118c89c08ca8,complete,false,true,81.1538,0.461538,1,1856,271,70.833,0.110144,1083,102,1185,1,true,3,false,false,false,false,false,0.697,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,67d8c8d6defa3fcec16dc2fae2ac3912dab0f5df80824fbc4fc16942854be001
tk-13,5a92488f53db6b709f8b582e76ca4d7173b507d75f74ed8265d825eb00b7a63e,complete,false,true,95.9302,0.883721,1,1562,109,71.975,0.088232,477,94,571,1,true,1,false,false,false,false,false,0.703,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,cb326002fa2739b42dac3739a5542c4b3c02f01ed1b2729935609153079761f0
tk-74,8256f4fa82b5f680c4d9c2582a83f6024149c090d8b4d51880c7e5ab3969e475,complete,false,false,62.2207,0.617021,0.625,1180,80,72.233,0.068458,487,77,564,1,true,1,false,false,false,false,false,0.676,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,bb5f311faea4eb59901c82daf1a43cdfe734d1fe72fcee571877d658895a5388
tk-15,f5203a267e40a1de75b12f6af33a821272a297012eb24e77db10446196a2d305,complete,false,true,77.3335,0.584527,0.875,4528,377,69.527,0.273035,1666,235,1901,1,true,2,false,false,false,false,false,0.656,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,a3abfe81370be4ded187600a091a4c3bdcf6ba9f74c4a3bfd57f4e0aadf235e4
tk-71,ad0051ec5ed30cf690101214d79828dc9ca06a08ede2fde0f08bf4f99e8d062d,complete,false,true,83.9803,0.774436,0.875,4746,816,69.202,0.261678,2995,182,3177,1,true,3,true,true,false,false,false,0.753,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,03ea0ab8538a295e5255f0239c87162f304b4db5e2088cba75c2937541c3f67c
tk-34,a48143f11166f76f2e7b8345e3fe65d8d4d29cd4dea200b110120f15801a6086,complete,false,true,69.6336,0.364532,0.875,2015,337,71.429,0.105147,1117,80,1197,1,true,3,false,false,false,false,false,0.681,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,f974324773e7c6554c7ae958c2a276b597a38c7070c6bbdc3bd826f36f248b21
tk-65,68eab73bd87be6abd159893ff2fe2d2685208dde390104110d874dddfcfdf231,complete,false,true,83.9831,0.542373,1,2178,269,70.98,0.124012,978,113,1091,1,true,3,false,false,false,false,false,0.681,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,f249d6851fa358379da29a1c0edd4b5e77ebfde7a2a50a57bb50239f701135cf
tk-57,3f9e96a8affa23e3e41db7ae4e2e4e22dc0a82e7959f46852794394149686bf6,complete,false,true,87.7907,0.651163,1,1909,109,71.197,0.095143,464,88,552,1,true,1,false,false,false,false,false,0.711,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,df406888ec8e31cfca3782bfa8eceb07b49a81faac462c175eb0d1ef89c3abf9
tk-14,8b6073ee1709d2b437c91c15a35a435da7f49c3a49fba2c74707fa1f9985e9ed,complete,false,true,96.1111,0.888889,1,2345,87,68.398,0.119848,499,108,607,1,true,1,false,false,false,false,false,0.703,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,52809e0fae79dccb905d3d8854f763c0ffd0ed8bb83c84add179ed7ce4533485
tk-32,5ac8d76367fbd887a4ab39f7e988eaad62e50f8ffd12868713c584d6ace61d67,complete,false,true,76.1307,0.318021,1,3505,255,66.825,0.199972,994,169,1163,1,true,2,false,false,false,false,false,0.654,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,506592c6518f98c6e64a3feeff6e42795ee2fb41a1cec1dba644cf2f68de9e25
tk-55,f20ff87fe52857b077d9bb645da22a694b423c1c67a85b2eca60374e80bfd11d,complete,false,true,100,1,1,2150,177,68.027,0.119581,700,110,810,1,true,3,false,false,false,false,false,0.673,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,b14ddd1224b88a356dab7f7cbcc35dda943b4f3f9fbf175e9f72e5497fc97fd8
tk-44,44682399f7fcd1cd2c218c3ab6bba50a6b0f8fc2bed22b561df135e542d72645,complete,false,true,78.9267,0.397906,1,1551,140,68.262,0.079646,623,77,700,1,true,1,false,false,false,false,false,0.698,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,44752d0197b41e2963f90e79b4e9f3979b7afcd2671ecc8ae4486d6f03e7aa81
tk-38,07e5a24c9fd370878f6ba70c47d2b44e2047c55dea14ab0a8607528477c9679c,complete,false,false,32.627,0.235772,0.375,2194,298,69.159,0.124434,946,111,1057,1,true,2,false,false,false,false,false,0.677,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,1a1557c25a1c623543633a5197cfab39aaa8088ad94a2d3af408d94e6f3dd3ea
tk-77,5c3360769cb78cb65f8fa675f7d25b64b40065b0a477b0164a9993d1e9a07dd6,complete,false,true,79.2593,0.407407,1,3236,341,65.741,0.19606,1096,180,1276,1,true,2,false,false,false,false,false,0.677,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,7fe31171716cf406c28a3cba4b834cf0fa015ad4077dae2c3a1543145bf60d76
tk-46,3c291b670e9ba535940b8d117aa4fcf5755323f5e203aed359d233abf41f56e9,complete,false,true,75.6555,0.536585,0.875,1742,245,63.418,0.0935,740,82,822,1,true,2,false,false,false,false,false,0.662,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,7d5196f61e8995a8e4c42d91e1bfe87e83d1ad60c4612801fe6a07a4f0fed3b7
tk-66,1403c0ea62c90f3795d06b058a571a7985a9d6a188f229639bf0e97dfc52e28d,complete,false,true,97.1311,0.918033,1,2231,230,72.237,0.136414,961,134,1095,1,true,3,false,false,false,false,false,0.691,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,d63211bf1edbe3d19ca864b772b784103e5c08a57bca15ffff0044f191b6ae47
tk-68,a090641bb0c48f6f8f73c3d979707a53b7d09520a3131c9eb97bdbf2d65c3989,complete,false,true,94.1667,0.833333,1,2281,335,63.779,0.124803,1019,106,1125,1,true,3,false,false,false,false,false,0.704,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,ff8f03c462f7268abafbedc92f95fd4cc781c702377f466a465cff2365417694
tk-48,461f1042cc4e47b74c286785514c68fd197dd33a06a8120ebfc19b1b58d6d698,complete,false,true,99.5977,0.988506,1,1493,109,67.068,0.078568,460,78,538,1,true,1,false,false,false,false,false,0.714,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,359cad11b2355371229127ad0a6ef201019afbc5364ee0aaaec0ef4c081ad3ce
tk-26,eae8db285776a7175b689b2a99d7642d828f9bc53ae6c30271ec91d6a8d5eb9c,complete,false,true,90.7895,0.736842,1,3364,248,65.059,0.179765,888,143,1031,1,true,3,false,false,false,false,false,0.69,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,b526edb99d36b303d7e6a284b83d62e365ececa232009b64694d49c787499062
tk-42,725c9d50bbbd82aef4be70f92013f10bd1d9c502441497fd9e16ea1ec0edb4e4,complete,false,true,99.0278,0.972222,1,6324,490,67.277,0.399493,1711,360,2071,1,true,1,false,false,false,false,false,0.696,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,cea603eb0a7a34629f949ce74efa141e2939cbb31697371ff648624e16f1b1ee
tk-33,dcf48f061b3e8b965224d2ce482d446e9e93f5d88e1b0c4afea440739f41ca5b,complete,false,true,76.2367,0.553191,0.875,2398,173,64.8,0.111642,637,81,718,1,true,2,false,false,false,false,false,0.677,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,5b430b9a6410180ee6a53dcf3ca3c923efc132e8fe82b54d62719b590f4f87d5
tk-20,df6c85f314f4b721d84e540e050037f168b77fe20d57b2eb8d074db5837f27b4,complete,false,true,87.4818,0.642336,1,2876,123,67.644,0.175154,534,180,714,1,true,1,false,false,false,false,false,0.701,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,21b727dc0dabdbcddbfa9ec7d0a34ea183bc3179aef942ba62eb4651c7ece3b5
tk-72,113cb3e020682a23b16a14aa0076c69de1d7fb98b212a70776b073c6d0d59d35,complete,false,false,41.6971,0.262774,0.5,2856,204,69.713,0.18148,842,180,1022,1,true,3,false,false,false,false,false,0.687,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,6d7a574227e45bae3f8876d3ef7ba4810254e04f760edd566b2df63f72e14e4b
tk-41,0b2cd386b0d7179a7451d0d4dcb6eccd4701af98c3e74f9675dbba4549d5af0e,complete,false,true,100,1,1,8605,524,47.498,0.458705,1844,336,2180,1,true,3,false,false,false,false,false,0.678,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,db82e218eb15bafcd3b5213ac041dc808ae7e883efed7e0a4260ff68e23e414d
tk-3,31e60792d8f9168ba0b08f0f90bead8d23fa4bed0cd3622c37127b2ecaca46f1,complete,false,true,70.7721,0.397059,0.875,1966,205,46.015,0.088626,729,56,785,1,true,2,false,false,false,false,false,0.689,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,4d9294cea0b1f135ec692ff71fb6d8e1993f7b50538a9d81f4312bfc1098650d
tk-24,5c15d936c223e492358e7542f8d70cad079b5d0e5b1d5a0a4df86ee65aff4d2b,complete,false,true,70.4741,0.62069,0.75,1965,371,47.106,0.094347,975,70,1045,1,true,3,false,false,false,false,false,0.687,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,8049c55e11adcf54ef94658c4df9907385056ad248e624a0c338a1a17fa96080
tk-35,adc8b24daeda8a8b228e0c9110804de2fdd0de7a8ab3e5ba59509eab113a4b36,complete,false,true,77.8736,0.367816,1,4668,261,48.154,0.232274,908,180,1088,1,true,2,false,false,false,false,false,0.666,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,a9e438eaed9fd0c5080fd178da252ab251f27f89fec448adab0c58c9b6774ef7
tk-10,8447012913808ee5e7c57876a607be252cc334937092a3e474b2aa68cd9e4151,complete,false,true,79.9548,0.891566,0.75,1873,372,53.623,0.093875,1120,74,1194,1,true,3,false,false,false,false,false,0.691,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,9cee50492b9ad92d8eaa76cc78e48714b746008736296d1992d648b621998d6a
tk-6,da4235dbc0ab77354cfafd563759506bb306c25df5c7e8bbc0e2e04db9f279b0,complete,false,true,93.866,0.824742,1,3815,233,44.244,0.16904,686,113,799,1,true,2,false,false,false,false,false,0.705,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,3dcc43d3c91819c8e7bc3b90e5497b2ab1c35c50671230455a8f4bf0a90b1ee9
tk-61,3c3d739a8db32d0f30c31ac18d1f92140d9b003127ae52af7dce20735324ad31,complete,false,true,81.2228,0.695652,0.875,4004,110,43.663,0.19757,501,164,665,1,true,1,false,false,false,false,false,0.712,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,0460339267e0f7663dc5aa6dbf401bb7d530d925d76b99dc5e259bfb8ba2a045
tk-8,01d51d930080df2207f15fe9ad1a7c574ba2c8a92f61649891215e4a50cda33c,complete,false,true,85.75,0.825,0.875,1950,93,43.84,0.093308,466,79,545,1,true,1,false,false,false,false,false,0.709,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,735ab2765618c570e9d22a6bff630c46463fc4deb69900e902021d386b79320c
tk-45,e2185a97fa2360d0b931039d77a8b6d07e725c643f3f84e5dccbb8f86b784d15,complete,false,true,91.6452,0.76129,1,4259,254,42.342,0.197931,924,141,1065,1,true,3,false,false,false,false,false,0.69,,,,,,qwen2.5-coder:7b-instruct-q4_K_M,brain,eeca4a344d09f30422c9f42e2ec341dedc1309eba7079e571ff6343ae79d8edc