diff --git a/leaderboard/entries/2026-10-14__claude-code__claude-opus-5-5.yaml b/leaderboard/entries/2026-10-14__claude-code__claude-opus-5-5.yaml new file mode 100644 index 0000000..9eb1217 --- /dev/null +++ b/leaderboard/entries/2026-10-14__claude-code__claude-opus-5-5.yaml @@ -0,0 +1,168 @@ +# Claude Code / Claude Opus 5.5 +# Source job: 55a40bce-1f7c-49fc-a270-83e770afe9a5 +# https://hub.harborframework.com/jobs/55a40bce-1f7c-49fc-a270-83e770afe9a5 +rows: +- metadata: + agent_display_name: Claude Code + model_display_name: Claude Opus 5.5 + agent_org_display_name: Anthropic + model_org_display_name: Anthropic + metrics: + accuracy: 79.29 + display_accuracy: "79.3%" + uncached_input_tokens: 6068472 + cached_input_tokens: 75625130 + output_tokens: 872778 + total_tokens: 82566380 + avg_trial_duration_sec: 223.56 + pass_at_2: 0.8317 + pass_at_3: 0.8452 + pass_at_4: 0.852 + pass_at_5: 0.8554 + pass_at_8: 0.8571 + pass_at_10: 0.8571 + n_trials: 140 + total_cost_usd: 62.92 + display_total_cost_usd: "$62.92" + status: display + trial_ids: + - 36a29ed4-a418-4e8f-a8e2-0052a99857c6 + - 6fcf825d-56ea-4934-b6e9-3a83e8825695 + - cba7d597-7eb4-4a48-a72c-d6c1cea0efbb + - 0f7067ce-d3f3-445e-9f43-01ecbd564b09 + - a572bf3e-d7d6-4448-a4c6-0524fe09083f + - b1c11b2b-ea86-407d-9f3e-2e6fb20e524d + - 1d327ba0-2ece-4064-a8a6-e781e4cfbede + - 45c1dd69-8b41-4620-935c-2cd855c1bf88 + - 6e50ff91-2e4c-4f74-8817-b7f5c4348edc + - a04909a2-d0cd-4a8c-8f9d-a50a5c4c65b6 + - 5cd1cf74-d37d-40d0-80bd-6b477a173014 + - 7b17b7a6-d3e2-41e0-ab6f-a112fc760949 + - 8b214c98-dd82-4f0f-8646-7ea8b366958f + - afdd1d85-1add-4aed-b7f9-9ef0eecaa0f2 + - 1f05d0a8-56d6-4434-b7ee-d60be6b38fdf + - bf1a1ecd-de20-4b03-9592-059e1b72a7b7 + - 7a656f5c-1e1f-4827-9bdb-ca805140a7db + - c16d0262-01ac-45fb-bad1-7d04e0a0c639 + - ee4400f2-86b5-4055-a4d3-1fe5203306d0 + - c02202d8-f000-4075-924f-b84ad9bff441 + - fbbee0bc-da16-4cb0-b0fc-cae40b3b9dea + - d825c33f-e1cc-4250-9ef0-1634dd513836 + - 270a7ffd-cad2-431d-88f4-a8d95c4bdb9e + - 131db03b-6b21-479d-a913-b817463b6bb0 + - 3655f0a4-0ff3-48e6-95ed-36ec3ad05839 + - 98465ad6-a8fd-411b-b16a-acaa6812f11a + - 228d83d5-a143-452e-a239-bd9b89dbd380 + - 76b4d764-f505-4f27-8f8d-34b06e393ff5 + - 08291cf3-ee42-48fc-9b68-77e6ee66b3e0 + - 8a95aa83-399e-4ffe-ad94-5417630b24d7 + - 2b732cdd-ab6c-4b64-9368-6756fc9e9b61 + - 9198f2b4-8309-4096-92b8-8fe228c76dc2 + - 11bd3595-d81b-413d-91a6-dcc81cdfeb2b + - 9382b5ef-cd94-43f0-8e35-feb469ce64e8 + - 73d54d55-97f8-4ecd-a08e-578a1b0dceee + - 2d43666a-ec5d-499a-a967-b5dc68eb03b0 + - ab860508-f624-403f-8122-19017ba47ea7 + - 3ac82298-7f84-41d6-8d95-a2a3717140fa + - 22e12492-0e9d-41fe-b241-3a3bfb96c223 + - 287bc315-4f8a-4d34-b89a-99eae3f0b89f + - 5e885e32-e5f7-4e90-8b4a-7995e39676be + - 0e82ec76-e389-466e-bcdb-621e404e1290 + - 6de7a4ab-e4de-4227-b27e-6047362cda9c + - 73f783b1-198a-4be3-9412-99e42d363ab8 + - 3232a868-d48b-4fad-a191-03b50e83601a + - 0a3a5621-3cf2-4ed9-8119-c078d3ffbcc8 + - 1bb3986e-f321-4767-a85e-fcb43bf2e201 + - 930dbdff-fb21-4f8c-8804-05271a58ac49 + - b4e75681-1756-4cd5-93fe-cda664df7980 + - 35955cc4-54ef-4799-9d75-d29b4a29ac5f + - f7a84500-cedd-4322-9734-cddfed7d6daf + - 79114892-3ea4-4c9e-8eae-4786249d0f81 + - a5ffec32-de75-4405-97d9-543c0bb7cad2 + - d495b02b-c65e-42fc-bde4-8e74d1bc5eaa + - 17a54dae-df80-471a-bf29-f8b1fe29d8dc + - 6cfa7025-1202-4edb-a83d-3cca6265df3b + - af421fd9-fab8-4a0a-9b2a-99c218596cfe + - 7a439731-5a5e-44a6-ae3a-3aa9c48480b5 + - 677f12d5-23b9-474c-a430-c0c766aa535e + - ac2fc4ef-7fa1-471c-bdfa-9e8c39a6efbf + - f1f2c512-bc9a-45a9-8871-84f891ba5d06 + - bec26f90-644b-40e3-b3cb-e1c11976da08 + - 563cccd2-2a64-4153-8451-43b4ae75befc + - db68189a-590a-4399-af47-0c4ac21b7a8e + - bb67163a-639e-49b1-a46e-a81b83135fd8 + - 53106083-b8ee-4cf5-bad3-8330860cbd1d + - 8fdca2f1-87b4-453e-82bd-974a34fbf239 + - 574ebb04-5389-41d1-bd1c-2c2fc271f3c9 + - c9cd6bcf-d532-402c-a8a3-780964a2355f + - 49490599-b67e-4411-aa8c-e32cbac10282 + - 05272e8d-5860-4790-b58a-7883c01a36b0 + - 4d6fbfb9-00f1-49e1-a8fe-a05e4a811837 + - 2e13668c-364d-45b9-808c-a2e73fb668ad + - a88fa01c-71c8-46a7-ab26-e6238c7b1149 + - 1ab92ede-969f-4bb6-8a7c-638d43383ba8 + - 347f3c36-dd2d-4373-8795-17c4736c4aba + - 2848f25b-6384-48e8-bfe2-1a61c596aea8 + - 81ca12c6-fb7d-43b7-85c2-3d7c5395c622 + - 6fd269f9-89a0-4099-a27f-59512afb88c5 + - 9c696647-ceb5-4e75-83cd-0b8f2bf898bd + - 29c22077-b9c7-4350-8a65-0b109b70e369 + - 39ecf5ac-398e-44e0-ba92-f75e7c953e95 + - 28a42531-3c72-4b73-93d9-57de8690a9ac + - 5d01d893-8ffa-4333-a024-f6f4286b67a5 + - 78de0bf4-9fa5-49ff-88c3-a788217fb50a + - e6da6259-6556-44e1-9e34-7d7c8b0dab3a + - 27090727-01b6-4921-952a-43c19a5de49d + - e2f9aa27-6d89-422b-9c93-7a76c995c7e4 + - 801176f3-9696-4282-be7f-27f0c21a849f + - 22bd862f-b5c9-487f-881f-ea03fedebae4 + - 159b7932-b394-41bb-8d2d-5f2ef5a31572 + - 11cd9590-66d1-4af8-894b-ef369a43af42 + - f26959cc-272d-4eeb-8a2e-6f793bbbf117 + - 8a368d96-2239-4a5a-98ef-cf5abfa97b68 + - 5d9ff37e-c7c9-4aeb-a15b-ac77c55ceca4 + - ed42776c-47cd-4f18-9048-54614fc35248 + - a5cb9992-be88-4935-b4e2-1d16852bd43b + - 57a1bc94-061b-45ba-b295-9b0ba57ec0d8 + - 14708b18-d058-4617-ba5d-c44f582380fa + - d981dd9a-e151-4f23-ac50-a6be9173326f + - df0d808e-292c-42f5-ba84-ba065ef95c4f + - 61b46aa5-fcb8-4ab9-aae7-5d033f14f850 + - 9188c7cf-0a1a-49f2-9add-f3009fc8a461 + - 742f8a05-149f-440f-b666-41f6e5d051e4 + - 29ae37e7-19ba-463e-9b01-6fb9644ab1a9 + - 6e9e45ca-095b-4778-8754-ace8fe21155f + - 703a90c1-5140-4f0f-ae4e-c0f14ee89e95 + - 09de4069-db2b-4760-a935-f5721e3e259f + - 7890e976-ae95-4df8-b3a3-15ef9a72206f + - d8f7c1d6-fa67-4a91-bbce-5eaa388f165a + - 63780686-9cf6-4e24-a806-4f13f4182c1f + - ed283623-f36d-4db5-983b-9235e260be6e + - f72913ad-2e13-400e-8751-1196c74e9f10 + - ab603aef-02e0-4db2-94bb-63a255873da4 + - 1acd0155-80ef-4a16-958e-632629a311bf + - 8c1eebb5-b565-40f8-b273-1a977d19c4f6 + - cbc3658e-1d07-4e08-87f8-9538339b68d7 + - 2a28652b-654d-4f8c-8a02-544763192d9b + - a7b1fe9c-823e-4457-9989-f48c6a6fad79 + - d13ae647-ed1c-4b18-aef0-8bf905923701 + - 0f2ff74d-5fcb-43b9-8e43-cabf79f285cb + - 7ba60c49-86ec-47d0-b418-1a4f18afdf13 + - cf7f26fd-6035-4f8d-97a1-3aab1767df5d + - 7ad304d9-8e9b-4e70-97fb-57c4170e1e73 + - badaf7bb-a677-4b1b-94f5-ce33aa679ad5 + - f3280ded-fb93-4e60-8603-a138692e4456 + - 59302733-6320-483a-b8f2-08eac28674ab + - 46a4e5b6-0f4f-4ff6-82aa-11a994f27710 + - d7ce6160-bd27-46f5-a65d-bd8955a547f2 + - 86de18f3-4a40-4fff-b790-ea5e2113f530 + - d2239ebf-9bfc-41a1-bf6e-81ecc3a93295 + - 75f0a29c-c0a9-423c-a5ec-b93ac4616177 + - a8a48da6-82f8-4d7c-981e-f325e44e9b27 + - e1e80367-3c17-4cf1-bf2b-65484c1b1dba + - 81fb04fb-9d2c-43b5-8056-60171afeaa84 + - 042e7639-1081-40c1-8567-df0c818be99c + - fa71fcaa-3415-47d8-926f-620a7c5274fd + - 2da7d44d-40b2-4040-b694-93a761a7f6b1 + - be601341-1f58-4df8-b71b-c92af013ebba + - dbe6d837-a641-427a-a727-4756430462cc