diff --git a/leaderboard/entries/2026-10-15__computer__gpt-6-astra.yaml b/leaderboard/entries/2026-10-15__computer__gpt-6-astra.yaml new file mode 100644 index 0000000..312bc4e --- /dev/null +++ b/leaderboard/entries/2026-10-15__computer__gpt-6-astra.yaml @@ -0,0 +1,169 @@ +# DevRev Computer / GPT-6 Astra +# Source job: 3dd7fbd2-a753-4ede-ad67-cca1eb4622c1 +# https://hub.harborframework.com/jobs/3dd7fbd2-a753-4ede-ad67-cca1eb4622c1 +# SDK-reported cost summed across all trials; not a gateway invoice. +rows: +- metadata: + agent_display_name: DevRev Computer + model_display_name: GPT-6 Astra + agent_org_display_name: DevRev + model_org_display_name: OpenAI + metrics: + accuracy: 92.86 + display_accuracy: 92.9% + uncached_input_tokens: 2859 + cached_input_tokens: 46334797 + output_tokens: 618011 + total_tokens: 46955667 + avg_trial_duration_sec: 205.66 + pass_at_2: 0.9794 + pass_at_3: 0.9935 + pass_at_4: 0.9983 + pass_at_5: 0.9997 + pass_at_8: 1.0 + pass_at_10: 1.0 + n_trials: 140 + total_cost_usd: 106.64 + display_total_cost_usd: $106.64 + status: display + trial_ids: + - 941d79b1-29ce-45ae-ad7b-35717b5e7769 + - 0bd79d80-3eca-49c6-b4d7-ee0060be734e + - 6cc486ba-72f8-4bfa-8ae2-1e879fd8902c + - 8b489fa9-ac34-4c5a-a5b0-a0de35427af4 + - 6e31ef69-41db-40cf-be73-ff2e05d64478 + - 225a8299-9a7a-4ef6-921f-de272913efbb + - cf34b211-afd9-45d3-80bc-7ba857ad6c1f + - e4a4d3f4-cb72-4511-9641-0c0302ea6bfe + - 88fbb9b4-5a0b-49fe-852a-0c163e6e0488 + - 3ff0b944-ebac-46fe-b71e-098f3810b226 + - 3edcf0c3-878d-42dd-ada0-0987bf15d3b5 + - 706bbc8f-ea98-464f-9a4f-066ecbda703b + - e324e1ce-c7c5-4504-8d3a-9ecec0c65ea6 + - 7c29f1ea-fd49-4f60-a25c-5e3b35860478 + - 3ca54925-36f3-4fad-852e-bff830d397ef + - b18ff0d8-cb4f-40b1-aef7-3ce65b7b26ab + - 872f6448-4190-42f4-9eda-29fc075852c9 + - 9047c6e6-31b2-4ed1-84af-bbea8d2d9a34 + - 836a03e8-8930-4dbf-a9e4-36b2a7dea62e + - d77300b1-e0e7-4bc4-8ade-fedc0e319992 + - 94b4010c-1cc5-41a5-9d34-1ab89c9cca8e + - f895745e-6142-45d1-8528-54dd7e02e337 + - dd014aba-110a-45da-8875-2535c629d7b4 + - 86a8fb3d-d386-43e1-b2bf-c01118362db7 + - c45061d6-f77f-4bcb-bc3e-0640b0560270 + - be29d236-eb51-4c0a-9f18-1baf5737fa09 + - 118ce95b-c835-4240-96be-7b0bb3d27607 + - 803e2d36-ea70-4e87-8750-0feef3280e92 + - 10a81365-2c20-49c3-9f7e-da7ae2eaa328 + - 92308753-8d8c-4c24-8517-1295a73f27dd + - 73013cac-e788-454b-9fd5-fa38951c419c + - a12b3cfe-c75c-4d8e-afc3-f65764ddd661 + - 40536e94-3973-4214-ae82-de89716a6812 + - fd9f5737-6546-4373-939b-4ea99bb411e6 + - b6ffb23b-e7db-471b-9209-783dfba9042a + - 39bb76f0-8aa2-493f-abbc-f09b9edfde36 + - 17bce9eb-e86a-486c-b971-7d9a9286a8fe + - e11684b2-eccd-458e-8872-5d966e1b5e59 + - e6b29870-7a14-401e-969b-1e9a84219d03 + - 2e20e444-c210-416c-acb0-9712348de91a + - 24e4608f-8d5c-48ed-ae0e-bca96211f2e3 + - 673ae073-8d23-43cb-ad48-b21c74db5e9a + - 9bd1fbee-fbd0-40a5-ae42-129e3744a925 + - ae48a309-293c-4cca-9aaf-581600e277fa + - 3cfbec63-222e-4346-b91a-0120f6fd0f63 + - 097ee4ed-f490-4cbe-9c9b-3634e5742146 + - b4167193-f3e1-4b03-8e8f-c740d66f92b1 + - 5d86a791-b3e1-4b94-b210-baf80b21a0d6 + - f146ac5c-880f-40c7-ab5e-509c3ec0e19e + - 63fcfcf3-fe6e-4bd7-a22b-d9df381f72ed + - f1a80b13-f939-4c3e-ada5-be73ad296884 + - d3ffbaef-0861-4711-9ec8-913bd385772b + - 0d284945-722f-49a1-b451-260587accdbb + - 39625af0-7978-4a64-ba20-f889b2ed1045 + - 8c67208e-c59c-40b1-be3f-259d4be6e19f + - 67e0700f-720c-40ed-b1d6-6cb6b47866d3 + - a77061c2-47a0-41fd-bf64-13fc2e936518 + - cc56bb94-de21-46dc-b382-03b761b33d1f + - 80d5d300-55bf-46c6-af54-ae3d74667a57 + - 4d5b859e-5f9d-4d49-9781-91314b6f9aa4 + - 33e95ec7-d047-47b6-95a8-97b8e1503ca7 + - 6e1a3bb2-9396-489d-898a-8fec26217a90 + - 668280d8-2f47-4721-acd5-5b467e7cabfd + - 47bd4ecd-04f9-4a1a-937b-0067fe20e36b + - 10eed685-5144-4cb8-acb0-0457aac608bf + - 729d99c0-e24e-46f2-9004-8e01dbbdfec2 + - e19a7764-0400-470b-baeb-69c680592767 + - e80350f2-fed1-4f3e-b88b-5e4811536a7a + - 80e5116d-377f-41b8-a1b1-50ad8e646f03 + - c020e71a-41a0-4df0-a209-030cfe56005c + - a9185d07-f84a-42c6-a553-a37cef6d9109 + - 9453c87d-9a03-4bda-9db5-122cadb3c5a9 + - 696e3bdd-df10-48ad-99a8-97e2b7c196b7 + - 410d2b42-c4fc-43aa-8614-b7dfa8043c51 + - 39e04e56-4b68-4cef-9131-bae24206c093 + - 1ef43bef-f9a5-4b03-9e74-d5b1c6a52b7c + - 0427fe17-fa2b-4107-add2-fd160510412c + - 28995d0c-242b-4d8c-8319-a29dc0731226 + - ff7d74eb-dc0c-4718-a324-24e83d76820f + - da433c21-2a9c-4e35-b3be-801db3d8dd42 + - 1f45455d-d0fa-4552-bdf5-b10160805a95 + - d84e20fb-0d28-4678-9d23-9594d7699be6 + - 8125a6e3-e8bc-4851-abc3-0fecb3148d49 + - a88a6e52-e59b-4c80-b3c6-c95e71780038 + - baac4bbd-58bb-40f4-be09-ac87704b7633 + - 330b4559-74f4-4941-94ad-fb443dd37780 + - 0c2fc532-e89f-4e68-9d12-da69479d3ef5 + - f3d8f294-a518-46d9-9df9-a46d1a56354d + - 197a7fcc-7aa4-45bb-9c95-4f2ec786309d + - d8bb2d6c-226e-4827-85b2-34bfc00a63ce + - 83090302-1de8-4390-9148-e87ee6715ea7 + - 771b42e1-c81e-4aeb-a886-c4d54c2c2655 + - 22c31d7f-34b8-491f-a1b7-e89064e8c3e0 + - 7ef6eec9-2cf8-4e4c-beef-bfb37e210f65 + - 19247256-f8ed-4d94-8e73-f70d27aa002d + - c006978b-015c-472a-8ee9-37f180e16042 + - 3ce36cd1-fdc7-4c38-80f8-fb5e48447bce + - 8dafb8a2-26e6-4f6d-970a-1fd2fd88be36 + - 8b8e4b91-984e-4d95-a4c8-ec08183b55ea + - ab5babab-5813-4b3d-b50b-8855b18900e5 + - fc50896b-cfd0-4a9b-9b75-8d38805f1cc5 + - 4691e621-6b96-48f2-8b40-266e01e5bf4c + - e064a759-3641-4295-b84d-c1a3de9679b9 + - 7331924f-7e1d-437f-a2b1-123fd7c387cd + - ffed3997-3fb4-4d8f-aa28-a68c10453f6f + - 2ae0c8b2-6e68-4cb6-bf68-2123e265f129 + - 3f78e7a9-ac0e-4a6c-a4e2-24b0de87139b + - 80ce6956-a03d-415d-88a6-cdbe0d506714 + - a327442b-c9d1-414e-b532-2d3f531c9d58 + - ee6d8a17-427f-40e5-a0a5-3e59b83e7a9f + - d93dc196-6a94-46ec-9645-bed591f3f53c + - 1a64e254-01c5-4d3e-a649-376ed0081a13 + - 18af1b06-230a-4c46-a460-b723d742591a + - 3eadeffa-0068-4fc0-8af1-3420de6e69ca + - 8203f76e-e65f-4ec5-ada9-49dd5618cea7 + - df77a1c3-d126-4588-833c-db507439b4be + - 782e5748-9d63-4616-bb22-6ee1e931c916 + - bccdab63-9a73-44f8-b729-c90eacd57d97 + - e1e45197-4d3c-42e8-8c2d-006c67287a6f + - c3347bb9-682a-4669-a142-57aa32567f94 + - df752ccc-2da7-44b6-b04f-0ae7ce0ca080 + - d3792acc-84a7-40c2-a234-ee62c11c6a56 + - a7ad7c9c-cccb-4c00-87bb-924235ae9a62 + - 16162da6-2bcc-48a3-ba62-0d4596fe833b + - 2232acd4-d7bd-4741-a412-6c7ba564faad + - 4ebd79f3-f2f7-4f29-b7f4-40f1637f7c45 + - dba74b73-ce89-4f85-a5ba-63c10a55749c + - eb1d15f9-6f90-4b74-ac77-c36be0223681 + - 94782059-57d0-48b3-99f9-5e5dc804c848 + - 7e9f9f53-c74f-4eb9-ae68-2f3e99d75e3a + - b06891c7-4011-4bae-8b49-60cc3d86555b + - 88566b6e-e7f6-468f-bd61-71bbf472a29d + - 9092c0ee-cba1-4522-8d3b-640f7826111b + - 143d4b3c-8751-462c-8cd1-cb70a7ce1878 + - ac3e8bd5-9689-43e0-8fce-328ec27de7e3 + - 8ac7ad5f-4538-4975-a686-b89c6f8dfbb4 + - b46990ce-b47e-451f-b502-03c7764f2c85 + - 39442728-ca8e-4e1e-9c88-876416ec6d2c + - 294869c1-ba1d-4459-b4da-6c48a4a5ad69 + - 976771d9-758e-4411-87d8-4f97a1892373