diff --git a/leaderboard/entries/2026-10-15__codex__gpt-6-astra.yaml b/leaderboard/entries/2026-10-15__codex__gpt-6-astra.yaml new file mode 100644 index 0000000..ebdf801 --- /dev/null +++ b/leaderboard/entries/2026-10-15__codex__gpt-6-astra.yaml @@ -0,0 +1,168 @@ +# Codex / GPT-6 Astra +# Source job: 60465aed-d0c4-4649-9506-bbb6ff4496b2 +# https://hub.harborframework.com/jobs/60465aed-d0c4-4649-9506-bbb6ff4496b2 +rows: +- metadata: + agent_display_name: Codex + model_display_name: GPT-6 Astra + agent_org_display_name: OpenAI + model_org_display_name: OpenAI + metrics: + accuracy: 75.71 + display_accuracy: "75.7%" + uncached_input_tokens: 6178441 + cached_input_tokens: 34533057 + output_tokens: 230644 + total_tokens: 40942142 + avg_trial_duration_sec: 176.75 + pass_at_2: 0.819 + pass_at_3: 0.8542 + pass_at_4: 0.8755 + pass_at_5: 0.8895 + pass_at_8: 0.9143 + pass_at_10: 0.9286 + n_trials: 140 + total_cost_usd: 123.29 + display_total_cost_usd: "$123.29" + status: display + trial_ids: + - 60b1dd14-790b-4f14-bc06-89f30b094152 + - 9de6f6ba-68bd-411f-b5dd-1599a909159c + - 43dc00c2-30e0-41f2-bbfd-43df1aea7dbe + - 8c6a08c4-cf43-4bf5-809c-81d0446289d2 + - c4d0d9a4-677d-4b4d-b5c3-506735481a92 + - 763d5b0b-9686-4824-9ffd-66336c5a529a + - 593e8a3b-ca94-4acf-b0f8-d7d619979442 + - 2993a36c-a348-43d2-b0f0-94b1ace874d0 + - f0b5dfb1-0a12-4419-b57d-b6ae139a5b78 + - 678e424d-54ef-41cd-9689-8fbc2265d2cc + - eeeafd2f-9947-4a12-b26c-2208db293dae + - afca7dc0-491b-4305-8d70-53bf692d06d2 + - 2aed32b3-5a9b-4e71-b1b6-e196c980cc7c + - 9920c371-6cc9-4d02-b54c-b86e039f2e5d + - abc6791a-3885-44b5-af0d-7eb0725acf92 + - 38845598-db0a-44c7-9129-ebd5d0ccece4 + - c343fde8-a2d0-4372-9fb4-646f6ad89e0e + - 03bea2f6-028a-4221-a4e3-f895a9cb7576 + - 60703a49-1f71-4074-a963-90abfefb0d53 + - 7e7a9654-a990-470b-a45f-9940dd5690af + - 04e575c3-d5e8-43fe-aa3d-a7b7bdbb4f48 + - c03562cb-475c-49ba-a76d-4098cff523cd + - 93854920-97be-4aa0-8085-b5ebefd7a0f6 + - 64a4dc82-31ab-4b0f-924f-87af9ca4365a + - 6927bf15-5104-4b83-8591-9813e7cc51c5 + - c92a965d-2ff0-49ad-b19f-1bc85bfa948e + - 16938b23-f4b6-4df4-a6e1-f2bf4960e711 + - ae42617e-25ea-457c-bb22-f03af9c1c945 + - fdf5e571-c1af-4f88-8490-4bbf56993096 + - b06e646c-1e12-4920-83b4-f2ee7f7d8300 + - 703fbddb-9b52-460a-9034-fab526a4ca0d + - fec5ccd6-8428-4260-8d49-69808612bc2b + - ea909882-5a53-494a-9a8e-36f39064ad5d + - 587a87f1-3786-4bc7-891d-d7a1e4309aca + - 65a4d00b-7291-4ed6-962d-8aaa618027aa + - 10e0855e-5755-4cf8-9b20-ac003b5635d2 + - dc6a203f-efa8-41d7-8403-d18982ff0dc1 + - e036446f-a2bf-41f5-8962-f619633ca020 + - abe3d24e-1817-4601-912b-d288d8bd718e + - 4707b9a8-b044-47ab-8541-e9c4aca5024f + - e75f39e9-f4fc-4e2d-8fe7-a1d023e19e09 + - 40178207-5631-4b54-b6fe-8860418cf6a3 + - 7a8cce8f-149a-4ccc-9813-8d8e42a5c2cf + - 8112b701-f2ef-494e-b45b-a7cf2ae49fee + - adac930e-5048-46e9-8abd-14e5e8baefab + - d5483ea9-8ea8-42d3-b652-1b4203f554e3 + - 890deabd-0f15-474d-9c15-95aa3c66f314 + - 3572a075-0c60-4a86-95c3-439016736cbc + - ee46cb9a-165d-4d02-b454-bac45d11fbbc + - 67794972-a322-4246-8162-a669a76ae7a7 + - bc675459-2559-4b0c-9ae3-7d2ee0237c7f + - 2284a0f6-d372-4597-901e-fe2984b333ca + - 9a53aa92-822b-4fe7-b189-973b23064190 + - 0d073b92-c8f4-47a5-83a0-234e9f885edd + - 2ab8e23a-35f7-48e0-8d3b-367a26326071 + - cdcd2235-6a5a-4974-9cc2-7b04bdb79515 + - d8e05beb-3fe4-4030-8a28-8c674d105f37 + - 1343f92e-e69b-4332-850e-56d8af195b50 + - 4fc69a1b-1268-4208-b95f-d7ce27b15fe0 + - ba916e6e-fc48-4850-a123-0227a2e0fc31 + - 1d4aaeb7-b420-4d32-a993-d6948517f8be + - 9f1e2a30-d356-46cb-aa73-57eb3c448ade + - 5c039dae-976c-4664-aab3-8a53d037bbc3 + - 16485ae8-6b69-4954-85fb-584f256acf21 + - 66ca0d76-9f64-41cb-9a84-cd500f2fe8ea + - 44b8f062-8e25-417e-bdfb-e1b19093ec8f + - bd53fd16-719f-4de2-b24e-b685bc4d1ea2 + - c391352d-deaa-48ec-9929-782901b4da16 + - 7e81667a-f7e1-4dc9-ac67-f3cc437e7057 + - d2e5beaa-c41d-4692-b8db-3ce9e8a4087a + - 820abc01-f179-4587-b825-8eb53a1d8082 + - 66d143eb-3eab-4612-9dcd-d702ef3f5990 + - ddaeb571-9246-4fe4-92c6-cdd5e1c58208 + - d09e2d6b-5565-4d29-8f5b-582ea980e221 + - 202d8328-6ac3-49cd-b26a-2f906b312b67 + - 2488261c-eb1b-4a41-a3cd-a2f9ac748e17 + - cf2fc497-bede-4669-92f6-a3b0885cd46d + - 0a623f54-e9a0-4b9b-85ad-f69298f2462b + - 3c443aa8-6f5e-4fc9-8b36-81a2cc021040 + - 07fb2a7b-6ca3-4f63-a1be-0a5f155554af + - bc4a1b64-fdff-4003-81ee-83cdb6fd10b5 + - 5fd7910f-1e05-4bab-8ddf-5fcff44a0bcf + - ca0d439d-a280-44e3-9cc2-8b686636d768 + - c6949736-c480-4631-a613-88c3daa2d717 + - 00d3f58a-fdaf-4408-8cc9-33baad7c0f83 + - ce4ca997-9efb-4aed-a5d2-b24fa89a3703 + - 13bd0080-88c2-4deb-ba75-ca5af21fc4c1 + - 4541f213-7d4a-49c6-9098-ae7c165feb5b + - c4efb6e0-0c8d-4375-91bb-bcd337a3c217 + - 727ffa91-ccfa-4cbd-bb26-c9fb1f2041e9 + - abe41e04-9dbd-4534-bb4c-f85dbe24e2c3 + - 5cd794d1-98f2-4756-a953-94c76fcfb2bb + - 00cbe886-43cf-4687-a200-610c33df9860 + - 7612c55d-a772-4f26-8556-7f75dd5cfb38 + - 6d143b86-39df-4421-bcb5-d66a530ca978 + - 001592b8-9f7f-4387-941d-ef3667950cd4 + - 13ce8179-5d9e-4e71-bd92-8c07096cd4c6 + - b7826365-ce18-48f7-ae32-df1c8ee2a1cf + - 395954dd-f485-46ce-a7aa-85fc089dfc70 + - c28713d4-74aa-4893-b391-b4bfb9b3c1ec + - 5e0f9b3f-7bce-4953-b40b-93d0480d25f4 + - f8540fc5-7199-45e1-a27f-c73f11c16522 + - 3187db2e-45c1-46e5-a11a-a085c8d63d12 + - 5fb0d8e0-f422-4087-a3b9-62e8b14edb12 + - 742b5f31-a1f4-4a77-add2-f3aeca427758 + - 4100657b-5f64-4dbc-8351-5c95f9f33b11 + - 1c08e162-94f0-4a8f-9b92-0d191f61301b + - 87f9140d-e8c1-4a96-b7f2-df1b2a131e8a + - b00746f7-8b82-46f7-a1dc-ffbc103ea0ab + - 7f33ff79-3353-4228-ad81-85ec6111f8f2 + - d704f00c-81f7-430a-94c8-10d8c4c00925 + - 870cbac2-24c0-462f-9786-2ae304fec70a + - a8a92339-9f84-4429-8a2d-3a1eea71660a + - 4fc554aa-8f62-4521-94d0-15cea55c328b + - 80f4575c-5254-4799-90d7-24a2173027fc + - 8e3849bf-58f2-4b95-8fdd-122239898351 + - 326173ca-fdea-4762-9268-9b5dee8e72be + - 83f904f0-11e3-4c4f-a1b8-636f3c88514c + - acea8224-d935-4fff-b5ef-c132c16a6fc5 + - 51fc30f2-bbea-42c0-9aba-bcc2759049bd + - 6cbb54b6-deb0-4e1c-a6c5-a9af4039d4e4 + - f364092d-4a7a-49bf-acc2-fe264e749e34 + - 31c91110-a1a7-4a6b-84e0-c602517cff58 + - c270ff10-9ce7-4372-9d4e-cf7de9f16fb7 + - 53f8eca9-d897-408b-be89-50ba27b318e8 + - c0d5da1c-bf08-4a06-ad1d-c1475ca01e60 + - 14f92582-e671-451d-abb7-0cbe6f5ee54c + - 20a59cc1-b217-4bcc-8e4a-db51ebeb0bc7 + - 4fff0a68-9132-4eec-8bcc-220206a67025 + - 0d6fb3dc-869b-4075-a728-5122e1e99471 + - f8fdc73d-257e-401f-bd01-f100bc69a8a1 + - c7b5f50c-818d-4359-b397-aa5498ec69f8 + - 6090cca8-2dad-40af-b679-3755c7145ba2 + - 4c001fe5-b657-4afb-bc37-0ab071d8f692 + - b2c0c954-1592-4207-b6c7-c54f135fb321 + - e0619f27-8f5a-40e6-9d4b-816c9c44d98a + - 55fc375b-9907-4a2f-91c5-e343a86663b2 + - 3bf4bb38-97f3-48f2-8221-a4f20ead8bf6 + - 61010951-3c41-471e-af1f-106d4b9ec0bb + - d4a05e62-ce37-44d6-ae0d-e8dc4b44ff3b