Benchmark Results

Summary

Total Tests: 188

Total Models: 16

Solved by All: 1

Solved by None: 15

Question ID Models Passed gemini-2.5-flash-preview-04-17 gpt-35-turbo gpt-4-turbo-2024-04-09 gpt-4.1 gpt-4.1-finetuned gpt-4.1-mini gpt-4.1-nano gpt-4o grok-3-beta grok-3-mini-beta o1-high o1-low o3-mini-high o3-mini-low o4-mini-high o4-mini-low
5cafd6c1-2f43-46eb-ac47-a5301ba0a61816
10ab786a-028e-4465-96f6-9e83ca6c5f2415
235b30a2-e5b1-441f-9705-be6231c88ddd15
56506854-89d6-46a3-9804-b7fde90791f915
0940a971-809a-48f1-9c4d-b1d785e96ee514
22c779cd-9445-4d3e-a136-f75adbf0315f14
2f898b81-3e97-4abb-bc3f-a9513898837014
31dad7ad-2286-4c02-ae92-274418c85fec14
4588d243-f24e-4549-b2e3-e627acc089f614
53cf1903-0fa7-4177-ab14-f358ae809eec14
7e91138a-8e74-456d-a007-973d67a0bb8014
9f9968a6-601a-46ca-b7b7-6d4fe0f98f0b14
bf23c7dc-1004-4949-8262-4c1d1ef8770214
d91473ca-944e-477a-b484-0e80217cd78914
ea79f937-4a4d-4348-ace6-9916aec453a414
f069f0f1-baad-4831-aa2b-eddac4baac4a14
fec27f65-db86-4c2d-b66c-61945aee87c214
1d5711d6-655c-4a47-ae9c-6503c74fa87713
2d5a61f5-0447-4be4-944a-1f8530ed657413
2d943c18-e74a-44bf-936f-25ade6cccab413
386d3850-2ce7-4508-b56b-c0558922c81413
6db1f57f-d1d5-4223-8a66-55c9c65a959213
727dbcdb-e495-4ab1-a6c4-80c7f77aef8513
94be7646-25f6-467e-af23-585fb13000c813
a768aaa2-2442-475c-8990-69cf33af0f4e13
b4115c7a-0e92-47f0-a61e-17e7218b243513
c5806a4f-62b8-4900-980b-c7ec004e990813
d5d5a6b0-0f92-42d8-985d-47aafa2dd4db13
02a91c34-8a5b-4bed-87af-501103eb535712
18136e38-0530-49b2-b309-eed17378747112
23d348f3-cc5c-4ba9-bd0a-ae09069f091412
33a29ab1-cabb-407f-9448-269041bf285612
3b3809b6-a54b-4f5b-8aff-cb51f2e97b3412
486e88ea-4f56-470f-9b57-3f4d73f3913312
68254a85-aa42-4312-a695-38b7276307f812
69119e58-96db-4110-ad27-954e48f3bb1312
7161b085-816a-491f-bab4-d68e974b799512
7906f0a6-b527-46ee-9026-6e81a9184e0812
85cfbf23-4a1e-4342-8792-007e004b975f12
85f3a526-4cfa-4fe7-98c1-dea99be025c712
9e8af564-53ec-407e-aaa8-3cb20c3af7f912
aefd6866-d753-431f-a7a4-215ca7e3f13d12
b854eb97-bf9b-45ab-a1b5-b94e4880c56b12
c0413fb5-33e2-40b7-9b6f-60b29f4a7a1812
c7ac59cb-13cc-4622-81dc-6d2fee9bfac712
cb01b3da-b0e7-4e24-bf6d-de522352678512
ee72b37d-b8f5-46a5-a9e7-0ff50035ffd512
f400d1c0-1804-4ff8-b069-ef5ddd2adbf312
3cfde62b-7c33-4b26-a61e-755d6131c8ce11
7784c64e-ed0b-4b65-bf63-c86db229fd5611
a50d5a97-2531-499e-a1de-5544c74432c611
c3a377f9-1203-4454-aa35-9d391d34768f11
d2b95631-62d7-45a3-aaef-0972cea9793111
d400090a-d8ca-4be0-982e-c70598a23de911
0709945e-4fec-4c49-9faf-c3c292a7448410
1ae5ea1f-0a4e-4e54-b2f5-4ac328a7f42110
3ea1f938-f80a-4305-9aa8-431bc486731310
5ff9d047-6e9c-4357-b39b-5cf89d9b59c710
7762e120-5879-44ff-97f8-008b401b9a9810
78a12e65-efff-4617-bc01-88f17d71315d10
7bcf83bf-f5ef-425c-9d9a-71618ad9ed1210
837d609b-845e-4519-90ce-edc3b4b0e13810
88ca025b-3040-44eb-9168-bd8af22b82fa10
8b3f4ed6-077b-4bdd-891c-2d237f19410f10
8e36da01-cd29-45fd-be72-8a0fcaad448110
95f5c72f-6dfe-45f3-a8c1-d8faa07176fa10
9636dd6e-7599-40d2-8eee-ac16434f35ed10
be8f4019-d8b6-434c-a814-53123cdcc11e10
d88a3d3b-d016-4939-a745-03638aafd21b10
f543635c-1705-42c3-b180-efd6dc6e7ee710
fcbdd43f-f4ad-42d5-98f3-0218097e272010
034fe21c-3186-49dd-8d5d-128b35f181c79
173126b7-afe4-45eb-8680-fa9f6400431c9
1f23bfe8-36d4-49ce-903a-19a1e8c6631b9
35727d9e-7a7f-4d0c-a259-dc3906d6e8b99
41410c60-614d-4b9d-b66e-b0192dd9c5979
83a95136-a496-423c-81d3-1c67501339179
a574dafe-a903-4cce-9701-14040f4f35329
f449c933-0891-407f-821e-7916a21a1a6f9
f9f2fe59-96f7-4a7d-ba9f-a9783200d4c99
1b99ef28-f83c-4ec5-8a08-1a56263a5bb28
4fd35378-39aa-481e-b7c4-e3bf49375c678
694b3cc8-6a78-4d35-9e74-0123d009e94b8
899a7fb5-d197-4951-8614-f19ac4a73ad48
952931a4-af0b-4335-bbbe-73c8c5b327ae8
a580462d-2c19-4bc7-8b9a-57a41b7d3ba48
afe369c2-b42e-447f-98a3-fb1f4e2b85528
b8a49f03-e3c4-40f2-b7bb-9e8f8fdddbf18
bc071188-459f-44d5-901a-f8f2625b2d2e8
f723d13d-48dc-4317-9990-cf43a9ac0bf28
039b4b10-2900-404b-b67f-4b6d49aa64997
20ef1523-8758-4898-b5a2-d026cc3d2c527
282f929a-6bc5-42b8-bd93-960c3ba35afe7
58bd8c8d-3a1a-4467-a69c-439c75469b077
62a06ec5-5754-47d2-bcfc-123d8314c6ae7
640cbf6d-659b-498b-ba53-f6dd1a1cc02c7
76f71e2f-480e-4bed-b61e-398fe17499d57
7c86c55c-70fa-4a05-83c9-3aa19b145d1a7
a315bfff-7a98-403b-b442-2ea1b255e5567
b1251c35-dcd3-4ea1-86da-36d27b54f31f7
b721c6ef-472c-4263-a0d9-37f1f4ecff667
c141bbdb-7fca-4254-9fd6-f47e79447e177
cada55b4-8251-4c60-819e-8ec1b33c93067
deecd55f-afe0-4a62-9fba-4d1ba2deb3217
11ba69ee-902e-4a0f-b3b6-418aed7d7ddb6
21fe622f-8e53-4b31-ba83-6d333c2583f46
251c5936-569f-42f4-9ac2-87a173b9e9b86
37807632-d3da-442e-8c2e-00f44928ff8f6
3c64f177-28e2-49eb-a799-d767b24dd1e06
3fb46e17-f337-4c14-9f9a-a471946533e26
4299eff5-90f1-4446-b2f3-7f4f5cfd5d626
53ead5db-7098-4111-bb3f-563be390e72e6
5f8e36de-37ca-455e-b054-a2584f043c066
6502c8f0-b775-4dbd-9193-1298f56b67816
6c2da894-0b57-43cb-87af-46ea3b5013886
6e0d1131-2d7e-4905-8ca5-d6172f05d03d6
88f6327e-51ec-4bbf-b2e8-3fea534eab8b6
ac9d0fc3-8aa8-4ab5-b11f-682cd63b40aa6
b51239b4-0129-474f-a2b4-70f855b9f2c26
c89becbe-1758-4e7d-a0f4-97d2188a23e36
d9c32b3b-7916-45ad-aca5-6c902da803196
edd779e4-a509-4cba-8dfa-a112543dbfb16
faab755e-4299-48ec-8202-fc7885eb65456
39e417dd-4fed-4d9c-ae3a-ba433b4d0e9a5
69f625ba-938f-4900-bdff-82ada3df5d9c5
8b87dd03-8204-478c-bac3-3959f6528de35
94500ae1-7e31-47e3-886b-c328da46872f5
bcd4c2bc-490b-4f91-bd31-3709fe75bbdf5
da75ae8d-26d6-4483-b0fe-700e4df4f0375
20aba24b-e61f-4b26-b4ce-4784f763ca204
3723ab77-c546-403c-8fb4-bb577033b2354
3dacb0d2-46ee-4c27-ac1b-f9886bf91a564
8dbfc15c-527b-4ab0-a272-019f469d367f4
8fe2ccfd-f079-4c03-b1a9-bd9b362b67d44
bb6b51e1-ab92-45b5-aeea-e410d06405f84
bdaebd56-368b-4970-a523-f905ff4a8a514
cccb070c-df86-4216-a5bc-9fb60c74e27c4
d0c88567-803d-4dca-99b4-7ce65e7b257c4
f4983098-bb13-44fb-9b2c-46149961807b4
34f0a430-9d04-4d98-bcb5-1989f14719f03
424e18fd-48b8-4201-8d3a-bf591523a6863
5c16ceb4-ba3a-43d7-b848-a13c1f216d953
5cb0b071-8a5a-412f-839d-116beb2ed9f73
6b1dbaf6-cc8a-4ea6-891f-6058569653bf3
9059e8de-3d7d-4954-a322-46161880b9cf3
a4651931-ebbb-4cde-9363-ddf3d66214cb3
af9fd58f-c4ac-4bf2-a9ba-224b71ff25fd3
bbdb06bc-bab6-4f5b-8232-ba3fbed51d773
be2590e8-4ac3-47ac-b4b5-945820f2fbe93
e16b3b75-dc9e-4cde-a23d-dfa2d0507b3b3
f45df6be-2e1e-4136-a384-8f18ab3826fb3
f4b26bce-4c2c-46c0-bcc5-fce062d38bef3
0b79c06f-c788-44a2-8630-d69051f1123d2
562d737f-2fc6-4b09-8c2a-7f8ff08284802
5d7057c9-2c8a-4026-91dd-13b5584daa692
6d99f93c-da56-49e3-b195-163090ace4f62
8fd5a296-6772-4766-9991-ff4e92af72402
b04ed73c-7d43-4dc8-b563-a2fc595cba1a2
deff4586-0517-49c2-981d-bbea24d48d712
fca246a8-a585-4f28-a2df-6495973976a12
02124c37-767e-4b76-9383-c9fc366d9d4c1
07ce871a-b3c3-44a3-97fa-a20118fdc7c91
090e5aa5-32b6-473b-a49b-21e843a568961
0bb64470-582a-4155-bde2-d6003a95ed341
510cc97f-56ac-4cd3-a198-d3218c23d8891
7a714703-9f6b-461c-b06d-e6aeac650f271
7af2b51e-ad1c-498c-aca8-d3290c19535a1
afb5e09e-e385-4dee-9a94-6ee60979d1141
b6ec082c-7384-46b3-a111-9a9b8b14e5e71
b8223ea9-4be2-44a6-b50a-9657a3d4e72a1
bb037826-cbe8-4a41-93ea-b94059d6bb981
db55f666-7cba-46c6-9fe6-205a05c3242c1
fdac1f79-b833-4bab-b4a1-11b1ed676a4b1
079ee2e9-6f16-47ca-a635-14efcd9941180
23b91cd2-c99c-4002-9e41-317c63e024a20
2cb4dbf2-2dca-4597-8678-4d39d207a3a50
3f627297-6c38-4e7d-a278-fc2563eaaeaa0
4cc571b1-f450-414a-850f-879baf36aa060
51005ac7-52e2-45e0-bdab-d17c6d4916cd0
54574908-f1de-4356-9021-8053dd57439a0
5898902d-c5ad-479a-8545-6f5ab3cfc87f0
75f66e03-37d3-4704-9520-3210efbe33ce0
7e7b62e9-5f83-477d-8935-48600f38a3c60
9be9b827-ff47-4e1b-bef8-217db6fb72830
a415f17e-ce8d-4ce2-a8b4-83b674e7017e0
b1a4d687-ba52-4057-81ab-757c3dc0d3b50
cf21060a-80b3-4238-a595-22525de4ab810
e22a9e89-69c7-410f-a473-e6c212cd22920