diff --git a/leaderboard/entries/2026-10-15__computer__claude-opus-5-5.yaml b/leaderboard/entries/2026-10-15__computer__claude-opus-5-5.yaml new file mode 100644 index 0000000..27cee70 --- /dev/null +++ b/leaderboard/entries/2026-10-15__computer__claude-opus-5-5.yaml @@ -0,0 +1,169 @@ +# DevRev Computer / Claude Opus 5.5 +# Source job: 839c0f26-fdfd-455f-82ee-4bef9e7d5c9f +# https://hub.harborframework.com/jobs/839c0f26-fdfd-455f-82ee-4bef9e7d5c9f +# SDK-reported cost summed across all trials; not a gateway invoice. +rows: +- metadata: + agent_display_name: DevRev Computer + model_display_name: Claude Opus 5.5 + agent_org_display_name: DevRev + model_org_display_name: Anthropic + metrics: + accuracy: 96.43 + display_accuracy: 96.4% + uncached_input_tokens: 931220 + cached_input_tokens: 50170504 + output_tokens: 913824 + total_tokens: 52015548 + avg_trial_duration_sec: 178.75 + pass_at_2: 0.9984 + pass_at_3: 1.0 + pass_at_4: 1.0 + pass_at_5: 1.0 + pass_at_8: 1.0 + pass_at_10: 1.0 + n_trials: 140 + total_cost_usd: 106.24 + display_total_cost_usd: $106.24 + status: display + trial_ids: + - 074f215a-8760-485a-b732-eef38221d005 + - 3f44ee1c-b3dd-430d-93d4-4d125d16b46f + - 0ba331f3-6383-463e-942a-1d177b8db920 + - f1c5ca21-1952-4f2b-b305-9c7efc05b2f4 + - d478e519-47d7-49c1-b1f9-d42e4a5c9d79 + - fa8cc32c-7e37-4cb6-9780-f619840b30d9 + - 6d1b563e-39c0-4032-8b03-c4319dc8bcc0 + - 351927d4-195f-4d94-be94-57760e32e87f + - 5cdc670c-be17-4a06-ba85-f4abe865117a + - 46f5b0a9-cb83-4c93-8292-189a4b77d55c + - 0ac06c6a-dea1-4fee-a3f1-24eabaa933d7 + - 9094de9d-5b29-481b-b67d-dc18ee188873 + - 65243d33-1433-4d0e-81c2-757ace5d7188 + - 98f9186b-546d-40f0-b66c-238efd4459a1 + - f94647a0-5b5a-4b35-b9db-7f2877c6966f + - a05d7516-a6dd-4d58-8ad8-84529c904928 + - 2a4e0a51-8ab8-4b11-87a1-251d3d006d22 + - 7a62eb57-8717-4d33-a6a9-555aa1e8f511 + - 0ae5edc1-6526-4674-9c40-f61ce03e8aa7 + - 03e7226a-127c-468b-8746-96836e4bea92 + - 5a7a5b14-ef3e-492d-a918-ce38d89dd029 + - a654a50d-c121-47ca-8c26-47e3f044c806 + - 5efc99e0-73e3-4253-a8a9-f4840723f3e9 + - 9e495c60-37e8-408d-88d5-cf7275b650aa + - fac1d7d1-2701-4eec-be85-595744067c7a + - f89c534e-b68a-4197-aeeb-e643e1bc72f2 + - 9b52c60b-21d5-475c-9a6d-1ea376e9a087 + - 595eaef0-21bb-4f9e-a05e-6d2b77133789 + - eb5bf0fd-377d-463b-9b42-647188b762a1 + - 3158c935-fc16-4858-b34e-26772b75924d + - 236b2951-0e2c-496c-b0b4-2e3d846d847b + - ecf4d1af-3170-47f6-aa51-1b8a37a40282 + - 7465db53-9e39-4147-ab5c-7660b5572484 + - 8fe24bf7-7e97-4f9b-9c0a-2f0a583ecb38 + - 54a7291f-2498-4ae2-8a6f-f66608ac0e1b + - 109a7b18-838b-44a0-9571-437b6b02121f + - 076928ba-8ca0-4fa8-9b1e-d7756d04daef + - cf6dc88d-6ed7-41a7-bf2b-3b5db5fcc181 + - 3a2abf24-cfb8-4eb9-bacf-78413f4eb28f + - 384f8f12-e737-4f25-b5dc-3b8ee0c2adae + - 68b65da3-c95d-49b6-97ff-af12db1a88ad + - be1d229a-8284-4303-abbf-d16f1eb96a48 + - d3252b5b-188e-43ed-83b7-ffa06f7c8c80 + - 2db96728-e194-4a0f-afa6-cabef5d28cae + - f89eebcf-fa5f-4235-8e11-b75c101b098b + - 0ad48d07-3f81-42c9-ace3-fde7b0b24cc2 + - 7ee252ea-7836-47db-837a-a85e66e57606 + - 54a8db38-e93a-414c-a15d-913db2c27a6d + - 59096f83-3096-454a-91ef-de2a589102e5 + - 49526299-825e-4e8a-b028-7ace77542524 + - a3b5495b-6f73-4873-8d8c-551d3b0f1fb5 + - 931e3cdc-5de4-48aa-9a9a-e4597745ceec + - 13f43008-71e6-46db-a568-3ba9e9ff6b78 + - 8dd8d06b-aad4-4738-b4e2-9110466c8bde + - cbf5d379-6773-4d0f-8218-9297bb4431e1 + - a446cc91-d5f5-4313-bae9-3111fc388ec6 + - b92a6618-39c2-47af-a9ad-3b8358c64286 + - 485f77ff-e4d6-48cd-b689-ab53e69ad842 + - 7fdfe084-8501-4074-87b4-ba2ea89bc783 + - 9c662675-eb29-48e7-8750-6498c08502e3 + - 3c3e9458-7165-4c84-b7e7-f82eb9cca6d1 + - 7aed248f-d953-416b-8da5-3555cdc3ffdb + - 3f278f25-2347-47bd-a1bc-fcbfa100da6e + - c25f8628-ef9b-4423-b423-12280b2c1315 + - f04c99a7-3bf8-41ec-a5a2-43bd7704b034 + - 51e2fe53-20d9-4a2e-a495-620c2282b8e0 + - 606566c6-18dd-4ba3-b7b1-01d422ea7e9f + - a788f925-17cf-4837-ba0a-845666345b70 + - d0936f4f-2e82-4adc-950a-ea3c3f1cfc37 + - 98ab5224-d155-47f7-bb97-4158d1757a3f + - 9c9a91da-33eb-4644-8bb8-9007dba4965b + - 99b1f580-4bde-45de-8b1f-2abd97370f02 + - f5629722-d541-4524-8924-375de0272a12 + - 31ae558c-dd1e-4893-bd03-8e9fa3620928 + - 8e8b493f-2d25-4c4b-ab81-ecf500721332 + - 6dfa93cd-9065-4d6e-b2a3-fc4a60b7584d + - 0f3428a9-7743-43ec-811e-570f00dcc010 + - 57b8e1c3-5c18-4104-9475-a1ef1b13e9a4 + - 0fb2ab5b-60a6-4094-9cb5-860231400cba + - 957544e7-62d3-467d-8ccc-ff194d380c33 + - 3775f15b-568f-4279-9135-1f12ac22dfb1 + - 9f140e97-6322-4386-9f84-055a9167b38c + - 6ef638eb-d507-43da-9d64-67fcf0a1c9f4 + - 14a03bdf-a08b-4b02-82c0-557ea5104130 + - 75df2e2d-2591-47b6-8a31-0cd3c9a360ba + - ec3aaa3d-9ebe-4335-b374-46f678874df9 + - b11f57c6-87b9-4b53-a1ba-fc1315697458 + - 1c07fe24-d169-4f44-b36b-654429019eb3 + - 5b79caa9-c39e-4c03-bf6f-c35a66b3316f + - 07b319f9-f8da-4d3e-b811-77d9cbf36d5b + - 011a6117-c417-4656-bd30-ebbee6fef610 + - ef64d71d-dc28-430e-97c3-1cbefed28cdc + - e098b108-81dc-4702-b086-5c2f03f199f2 + - 5c071912-dfdb-4714-b64a-eb6c4ece2eba + - 38c0ae78-7cbf-484a-b657-8d20391ce162 + - 8e10e772-aeed-4ed7-b19e-c43ab6b9417d + - 78ce261c-b0ba-4f2d-aba8-7eadecc85e04 + - bc883615-8ef1-4e4c-9ee5-0cea75860b23 + - 9f01325e-4000-4caf-be28-1c658301ecd5 + - 1077b6c8-7b03-4265-aed5-2456ca9b48f1 + - a205eaf8-44f2-45d3-9c50-cda9dd76e58f + - 06d7be6a-d40e-48a8-b700-681d695beb1e + - 03d617d4-4e0d-43ca-8e0a-9b5858b10856 + - f1165434-f3f1-4c50-8a1f-139ae70058cc + - b1f94aa0-d02a-43b4-9eff-388a304e7093 + - ab162783-8096-44f9-8ca1-25fabe7350ad + - 44166eb8-0521-4247-8dc4-fe4eeec3309f + - 386f0f7d-bd1d-4886-875f-a96d2c4fdc20 + - d98b8397-921d-4179-b097-4e239bcb7b88 + - 453d4298-9c03-432c-8414-dab547b243df + - 4084ca58-54eb-458a-a69e-29a4262af798 + - 8e953174-be9c-46eb-a540-5ff7daf3d6ae + - c019e639-1991-424e-825a-0e84efddbcc2 + - f4b976b8-65f4-4d3a-8ae0-d239009b35ae + - 719ea3d3-a73b-454f-a6d5-2e0c05ee5c9a + - 29f4e76f-8fac-454f-89f9-04fc4a7f2f43 + - bf5d7d75-45fb-4423-ac0d-28d15dc3ce1a + - e22e5b85-3b87-4cec-818d-5b7ab2166f88 + - 2c84c53b-93d8-4df4-9ab6-adf58baf5215 + - 5852e8fc-7413-4330-811f-913bddfd2a40 + - e70b177c-9833-4284-8373-9068eda1507d + - da278938-a611-4952-87bf-2814917cce3e + - bfe7eec9-553f-40a4-b6a3-d7e3b6914392 + - 5bff013e-e322-40de-8ca7-2e78b36f1454 + - 0fac58e6-306f-4359-8e0a-ce6eab96bd60 + - 325bedfc-0538-49aa-b54d-f0952d6a13ef + - 80fd4df4-823b-4c59-b0fb-72d7919712e3 + - 506fc6a3-a1ea-4883-b6af-4ff2df0b9fb3 + - 752ade3b-cdec-4b88-af03-0c5b4630a335 + - 9b07cfd8-7d21-4ff4-b399-1fd9f485505d + - f7c0c0fe-67bc-4fcc-8b33-cdd1cf4ad57b + - b53beeb2-26e8-42c1-b71a-08f920a513d9 + - d647a157-e4dc-4e74-9749-b842e1c30932 + - acb192e9-ea56-4780-b48c-61ee7316b481 + - 257a2eeb-a942-482d-bc1b-e589f79c2b7a + - dac933a6-3359-4cc4-aa63-935c7bf4973f + - 6c5d09ee-45b5-46f3-8adb-98eb6d8b3e73 + - 81599a4e-228d-404d-b395-dd062a632add + - 597739ff-2c97-46eb-a4b4-306cc848ca89 + - 561c269c-38b3-4228-87f1-2169272c65e7