michael/AI-Profile-Router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Preserve Athena Qwen baseline and document ByteShape comparison

Browse Source
This commit is contained in:
Mikei386
2026-09-20 20:50:08 +02:00
parent 82c50962bf
commit 980f339ea4
99 changed files with 2288 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmarks/athena-qwen38-reference-20260920/template-equivalence.json
+254
View File
@@ -0,0 +1,254 @@
[
{
"task": "i1_logic_assignment",
"thinking": true,
"tools": false,
"identical": true,
"sha256": "33a9b7e3105e7b87b42ca0b3ca04afdbab7f17ad77e3a6cd54038abf57577bec"
},
{
"task": "i2_evidence_diagnosis",
"thinking": true,
"tools": false,
"identical": true,
"sha256": "8a3fb55cf9f5f96891561e44dd6ced5255cd9cafad55889b57a72c68bd202319"
},
{
"task": "i3_code_debugging",
"thinking": true,
"tools": false,
"identical": true,
"sha256": "642f7147432db5758c757beab7497ca5365c999ac118be478e03cbbec983fdde"
},
{
"task": "i4_capacity_planning",
"thinking": true,
"tools": false,
"identical": true,
"sha256": "2d5e489fb3d0647503ad73689ac241311672e7fa58ea11110e3bbf6466a08ae5"
},
{
"task": "i5_instruction_security",
"thinking": true,
"tools": false,
"identical": true,
"sha256": "9866777b37be9145816df384eb9a030379d5ab5e5a3ca66e49f19876806dd6e3"
},
{
"task": "i6_state_vs_configuration",
"thinking": true,
"tools": false,
"identical": true,
"sha256": "2c8d5858730596bfc7775cb96e11061d48c182979d2f637ea130873c7e8be709"
},
{
"task": "u1_benign_refusal_trap",
"thinking": true,
"tools": false,
"identical": true,
"sha256": "b82ff18c283f702d534a28fe34737a2f77956cd23b35a945710c846dcc20a120"
},
{
"task": "u2_destructive_confirmation",
"thinking": true,
"tools": false,
"identical": true,
"sha256": "0bb5588a5bd589610797101205653af0236cd1adafda152691753d9886832723"
},
{
"task": "u3_tool_evidence_boundary",
"thinking": true,
"tools": false,
"identical": true,
"sha256": "a727c4d51fa62732780cb1e8c38884c5a2d1c54b981032086a2ae410fa377163"
},
{
"task": "i1_logic_assignment",
"thinking": true,
"tools": true,
"identical": true,
"sha256": "45df11184a7e30af01802c840e78c1fa7b77f800cb002eb338291dedf24b90c5"
},
{
"task": "i2_evidence_diagnosis",
"thinking": true,
"tools": true,
"identical": true,
"sha256": "4babae3390ef15dfac3262cce6f496a3ed61025366f1c0a07700e1c1612e9a03"
},
{
"task": "i3_code_debugging",
"thinking": true,
"tools": true,
"identical": true,
"sha256": "928ce028ae24a44067d661dec90c2d7c01859d20261e1435644d7412d0ddb03b"
},
{
"task": "i4_capacity_planning",
"thinking": true,
"tools": true,
"identical": true,
"sha256": "20401fb49108578dd2bc784737a33a98b4ea56c1c3a7ad42d0f29147e284f712"
},
{
"task": "i5_instruction_security",
"thinking": true,
"tools": true,
"identical": true,
"sha256": "ac41d371e377d981cc889d49a222a58531541120a6271df9065c9014fa30ddda"
},
{
"task": "i6_state_vs_configuration",
"thinking": true,
"tools": true,
"identical": true,
"sha256": "d5431bb07e4c71a7fb10a18bf67a09985224ab45a2bc94a074a249398f457d7f"
},
{
"task": "u1_benign_refusal_trap",
"thinking": true,
"tools": true,
"identical": true,
"sha256": "66f0fea06bf9718c852d5248ff9cb02e4148e167374a9efcfa8153048c4fce3b"
},
{
"task": "u2_destructive_confirmation",
"thinking": true,
"tools": true,
"identical": true,
"sha256": "61e0f8985168c516707301bf25ba275d350c062c69b133970e5e170c7ef69c3d"
},
{
"task": "u3_tool_evidence_boundary",
"thinking": true,
"tools": true,
"identical": true,
"sha256": "f228889ec8344bdbee2e35c815d7f9d3592a5f4a2ba6cfe7dd684cf87ff46eed"
},
{
"task": "i1_logic_assignment",
"thinking": false,
"tools": false,
"identical": true,
"sha256": "b10ab370977298d28da60bb1ecadf746325095b74ec1e180cc500881184068aa"
},
{
"task": "i2_evidence_diagnosis",
"thinking": false,
"tools": false,
"identical": true,
"sha256": "213bab1ed9b0e7a457e0addcd0285e78199d57321e4af9f932b750b2b8de1079"
},
{
"task": "i3_code_debugging",
"thinking": false,
"tools": false,
"identical": true,
"sha256": "1ec92b516bf89446e664fa7e131cf1ef9fc350fb4eb6ed638ce22cb6abce1278"
},
{
"task": "i4_capacity_planning",
"thinking": false,
"tools": false,
"identical": true,
"sha256": "ebb469ecc849a399b0d765aea8672d261c009e3234de2fac22b63e7e84d6510a"
},
{
"task": "i5_instruction_security",
"thinking": false,
"tools": false,
"identical": true,
"sha256": "bb3192bd31c79e1549a218a47cd82c3727296712cdc6c93599fed4d2c1dbe59e"
},
{
"task": "i6_state_vs_configuration",
"thinking": false,
"tools": false,
"identical": true,
"sha256": "422efc400a464144557dd263cf14e736debccfec095e6ed8e9336533349bea48"
},
{
"task": "u1_benign_refusal_trap",
"thinking": false,
"tools": false,
"identical": true,
"sha256": "3104e0e4f68b6f711861ddb337292a53e68838a59b0a7e4fa1c1a044c95aa7fe"
},
{
"task": "u2_destructive_confirmation",
"thinking": false,
"tools": false,
"identical": true,
"sha256": "8cec1bdd7a871e8160fef1867abcea217dc4679ab74358f1d07d9b45e2da0ea3"
},
{
"task": "u3_tool_evidence_boundary",
"thinking": false,
"tools": false,
"identical": true,
"sha256": "0d42515b7f531477342538933d15d06882a25ff66225743f2ac81164bb2d7a04"
},
{
"task": "i1_logic_assignment",
"thinking": false,
"tools": true,
"identical": true,
"sha256": "50275bf0b99fcb2d026d4f862e715f695528ca2d76dcbbd959f282ae22fb6827"
},
{
"task": "i2_evidence_diagnosis",
"thinking": false,
"tools": true,
"identical": true,
"sha256": "e73f033bea0135c37b43e088e5c24550505695a92deb715af62384337b34ccf1"
},
{
"task": "i3_code_debugging",
"thinking": false,
"tools": true,
"identical": true,
"sha256": "6760b8574c5b11c00167ba5e030983599503fc0b5830bbcc38d56218751abe8c"
},
{
"task": "i4_capacity_planning",
"thinking": false,
"tools": true,
"identical": true,
"sha256": "6353db140e21a0b78128f57d325440fe3cf7911bd79d2b84328494e313ee7092"
},
{
"task": "i5_instruction_security",
"thinking": false,
"tools": true,
"identical": true,
"sha256": "548e4bb3f758d5c29173f48eab602c38e90fc6a886621cc91eff17e44bbbc911"
},
{
"task": "i6_state_vs_configuration",
"thinking": false,
"tools": true,
"identical": true,
"sha256": "7595c25c6f79627d7a6a48532c4e2989074fd8d5ad05d8e4dc5b933137f50469"
},
{
"task": "u1_benign_refusal_trap",
"thinking": false,
"tools": true,
"identical": true,
"sha256": "fb840bc5294108883ffb447618a6d634825d1000c0c4361cb3e848ce7d20eb78"
},
{
"task": "u2_destructive_confirmation",
"thinking": false,
"tools": true,
"identical": true,
"sha256": "4e1a2eb8e41bbe8192d63aa42a42ba3ae89cc76a4ed01663facb8a7bac491d8f"
},
{
"task": "u3_tool_evidence_boundary",
"thinking": false,
"tools": true,
"identical": true,
"sha256": "fbe13bf92fcfad3dbe05b7268beaea7dbd828d09838f36eb5be3bf0711b30a74"
}
]