From e29bb2898140bb4b9f85e2347b278d8a327c6d89 Mon Sep 17 00:00:00 2001 From: c-suvamsa Date: Thu, 15 Oct 2026 08:03:20 +0530 Subject: [PATCH 1/2] Add v1 leaderboard entry: Claude Code / Claude Opus 5 Co-authored-by: Cursor --- ...026-10-14__claude-code__claude-opus-5.yaml | 168 ++++++++++++++++++ 1 file changed, 168 insertions(+) create mode 100644 leaderboard/v1/entries/2026-10-14__claude-code__claude-opus-5.yaml diff --git a/leaderboard/v1/entries/2026-10-14__claude-code__claude-opus-5.yaml b/leaderboard/v1/entries/2026-10-14__claude-code__claude-opus-5.yaml new file mode 100644 index 0000000..7587fa0 --- /dev/null +++ b/leaderboard/v1/entries/2026-10-14__claude-code__claude-opus-5.yaml @@ -0,0 +1,168 @@ +# Claude Code / Claude Opus 5 +# Source job: 4ae322ea-aab2-4b6d-b1ca-d27abdfd7152 +# https://hub.harborframework.com/jobs/4ae322ea-aab2-4b6d-b1ca-d27abdfd7152 +rows: +- metadata: + agent_display_name: Claude Code + model_display_name: Claude Opus 5 + agent_org_display_name: Anthropic + model_org_display_name: Anthropic + metrics: + accuracy: 82.86 + display_accuracy: "82.9%" + uncached_input_tokens: 8885443 + cached_input_tokens: 138601236 + output_tokens: 1771211 + total_tokens: 149257890 + avg_trial_duration_sec: 309.24 + pass_at_2: 0.873 + pass_at_3: 0.8929 + pass_at_4: 0.9044 + pass_at_5: 0.9127 + pass_at_8: 0.927 + pass_at_10: 0.9286 + n_trials: 140 + total_cost_usd: 169.11 + display_total_cost_usd: "$169.11" + status: display + trial_ids: + - a20d12ba-2068-49b0-aaab-6679f2446d43 + - be955470-7001-4d15-9984-c38b7a7f3fa0 + - 5760bb9c-b64f-4f02-bdac-4d8dc6412a4a + - 9e13ef96-057e-48d2-a1a4-1ea1a2df358a + - a16dd4ff-4984-477c-86bb-085d9817a71c + - 7f4a317a-6e40-4c7a-9484-83956db6238f + - 9f8083f0-f3a0-495d-a163-ecfc9ab94a9c + - f5b9efb9-bcbe-4dea-bd2a-90eb375a7632 + - 9814c289-3a87-4e19-a31f-fa19ce997933 + - d9815714-4820-480f-85d6-d3e59c9acea2 + - 98eb9224-e6e6-4b3e-b7ab-012aaa070aab + - 11560c7c-04c9-4643-9eb4-6ef6bec84dff + - 29bdaa70-1de4-4b34-940a-1d498d38bc52 + - e54395b5-1c56-48cf-9d2e-0bbc82038ed9 + - d4190fc6-f0a9-4ad2-ba47-2f52653adde0 + - a7847b51-820c-4d78-9e3d-1a73e9630ad7 + - 08122b36-4da3-48b2-907e-698baa380c10 + - d1ce8dda-1641-4cd9-893f-95c60854612b + - d63e2986-c448-4859-89dc-af4fea632aaa + - 136d8b8e-5130-4aa7-b68a-31f5357dad68 + - b9bccb5f-79cd-463c-914b-23b1b689dec7 + - f211221e-f5c8-4fc3-ab34-cc283cdd385f + - 8e3d0e39-d76b-48d9-89a2-609690015090 + - 34835529-b06d-4027-820f-35b70037c64f + - b80e4533-1690-4b74-985c-26469380a92a + - a5b01be6-b6e5-4c56-ab4e-42c36e212d04 + - 08994806-d831-4daa-8ae3-d0eacc35e42e + - d4b1169f-ff1d-492a-8cfd-c2c75a2b8087 + - cb828747-c35d-4b1f-8f5c-df1654659ba7 + - ca7a693f-c2cb-4e84-9220-7c6b9ec41704 + - 5dd01d84-6888-4b4b-9b35-f7facb9b474c + - f108eaef-0ff4-48b7-8512-32ba01e4d756 + - 90fccbdc-49ab-492b-a626-6538fc7c3b9a + - 76940009-e3b5-4a8a-9813-1de17f3c1f9e + - 462440c1-1cd1-453f-b9ac-aa423dbc9250 + - b5ed18ea-7c29-401f-832a-cdfd2b1a1638 + - b24e22ad-c80a-4b98-afb0-366a26764e82 + - 9d0dca19-0af7-45d9-b8db-d3fad54709c0 + - 98febc5f-8753-4516-b418-35625f0bd0d2 + - c98a145b-e01a-48d6-9f65-719aebad6819 + - 8d20df46-cd3d-4e57-8b21-215dc02a7886 + - f8570e7c-9435-46c4-9bf9-75367c1f1656 + - 4ecce8e0-f227-4207-a73d-0ce056d47e94 + - 53ecb2af-52a8-4441-b95a-9d80efbc5465 + - b113ab89-573d-455b-8f37-f87c6238e4f5 + - 8e563ab0-7930-432c-a477-b4ac857d4a0c + - 43ece841-4cc0-424a-8cf2-e3d9c4f46b86 + - fc2bdc26-f0b1-42b8-818f-78f29eae0653 + - 987a53a1-0bab-4165-848c-1e21229d33e7 + - edc45d62-6629-4928-9b9b-d40951220331 + - 4ebf903a-38a3-4251-a52c-ecf774a3f505 + - 2d08de39-eeda-4cf8-ba87-98ccfaec7393 + - caec3969-f3a7-4768-a465-3b1ea0120a0c + - 8cd67d31-a4c9-4be6-9a5a-66abdfbc379a + - 6a091018-701b-41cf-90fa-8381ac46fe65 + - c623af17-6851-4040-8161-bad235313d2a + - 499ec1ca-af54-4e93-b40d-76dfcd0e33d7 + - 7fa6f1a9-aaec-4093-a6f3-adae37e78164 + - 9a9a347f-f36e-4512-a0e7-d112961b726d + - 63cfabac-7182-4879-8cbe-96161d45125d + - 4957dd66-8ca5-46aa-bcd3-4223ebeacbbf + - 44c082a9-6736-4063-a2dc-f4a932ea2571 + - 109324bd-9cdf-4f3a-bc9a-736bf64bb941 + - 578840d6-ccd4-4929-9f64-a3c6d2ebc855 + - 0d4d1c4f-d1b5-4eb9-9ba6-4dd04b2a011a + - c3a480cf-21ea-4c72-b99a-8ec3c90e3336 + - aab2492d-a41b-4852-a839-bcda264fdcb3 + - 8ae85bb7-d6f1-4b91-bdba-2b25fa05701a + - 302bbcfb-5919-4a47-9b44-e8edada06f1a + - 0d81c470-8284-4902-a514-3fe92c337de3 + - 9ea531fb-baab-4bf8-a8ba-6618eb0c83bb + - cab12ce3-6b75-49dc-8a5c-f41b7255e773 + - 62129dbe-72a8-461c-b0cd-9beccb7751ad + - 0b3717bc-fe83-40ce-8bd9-0c16de1c7d37 + - ef0c5291-9821-4475-b275-623873661a88 + - 2e7e0314-c2c6-42fc-8fe3-e39bbbe05acb + - 2cd761b5-7cc3-4f48-8721-cfdfcd59485a + - 64d9cd4a-c871-4a69-8eed-be644155ab11 + - cca04b14-44b2-4677-a370-a5810dae9cad + - 02c42ab1-2854-472d-b99d-cdb2c7975950 + - 1cfe813f-6e61-4276-9ff8-515281a5c349 + - 3a11f3b9-9a09-4c35-857f-1eba00f85518 + - 66880489-de67-4e8e-a99a-47b024938bca + - 2f925e5a-abf0-44b4-abeb-38deef35dfbc + - cbb316a6-8c3c-4083-9497-fde2fa3388f8 + - 2680fbf9-2758-4edd-9149-7edfe9247fd7 + - dc1cb78a-afad-498d-b32b-984c19810f7a + - 634c0e8c-6789-4b42-b229-89a57d03ebe9 + - 4c0487ea-829d-4a78-8ea5-1bb74435875e + - 77b6f142-c431-4488-9ef8-e46ca217ed5a + - e1535640-1f93-4c29-ac45-dac096aad9b1 + - 464e0bf8-dfee-45fe-9d15-16d63d53179b + - b4ca40c5-3c98-488c-80d4-db805d8721d1 + - 49494c8d-fc76-4c58-b317-369954cadff6 + - 82493e06-d9d7-43df-8d0c-ff77d60ec507 + - 4d4cf5c8-12ce-4cf6-964b-505581c2f07c + - 8b2a0f11-0aa4-4e15-9fe5-37c24f5466e2 + - a662bb09-38d7-4dfd-b2a4-8d03d9578f7b + - 00410233-44ca-4201-a400-ae722e815146 + - 709ec3b4-b743-4a36-8a91-31347fdacf88 + - 745f3be2-d5a1-438e-86c7-ac6d905a8496 + - 9a5e9d29-13cf-46b9-b207-783afc65befa + - 4af60fe6-c86b-41a9-af33-5fd776f4d6eb + - 24e73f6a-8810-40f0-a203-91dc37b8bacf + - 17092ffc-ac99-4f8a-8da2-80d443c29745 + - b53fe6b0-e9e6-4517-a104-cdea7ad26979 + - fd2e3e8d-47a3-4155-88ae-fe193a057c6a + - 8f9958e3-8810-4c0e-a8ba-d9b089fab3d4 + - abe0a62f-1593-469c-a11e-85d86e6d2881 + - 904bdff8-e4ab-4f92-a5e9-a4af3426e2ad + - d46bc84f-0954-43a0-8ff7-ff2fc8a8a9d5 + - d14088c4-ae98-45ca-9391-2cf3bb8619bb + - 94794c5a-3929-4df4-a890-4377ebb048c7 + - 30ad9850-216d-435c-80bd-2afe82637ec4 + - 57067a41-7397-4cc0-be0d-ac8ec53878e5 + - a1c022b6-5609-41f5-b4cc-8bbf432f5fc2 + - 35aba745-869b-400f-a2ac-ace9fac25b3e + - e10ab838-d4d8-46b9-a3c7-5213f52b44f5 + - a75a33a1-9202-4b3d-9314-686857d04e12 + - 3f9faf2e-7b56-4293-8e8e-82d155d7452e + - b9bf8e51-c68c-4e4d-a2b6-b4beb85a8ee5 + - 8d7d52c3-de2f-4547-92b3-71a67abb1e22 + - bba0f311-945b-4a1b-a4df-40fbb0629401 + - d15cedf7-d8e1-4a65-8359-06f8fa9a3644 + - e648e0b7-13e5-434e-9822-57726ae6dfb3 + - 4c93be30-138d-447f-8ef5-798c8bf3ff7f + - d6bd4198-d6df-433d-840d-74126c37ae65 + - c539e684-ad1b-4df6-a247-6597bba459ef + - 25b143b1-495e-4a8d-b175-9eedde81b6e8 + - de5d4334-593e-40ee-b6c6-e03c9eadd55f + - 20661d02-67cb-45f7-8925-b7ca63d51235 + - 9b74451f-8705-4bbe-85c1-33e4fa7b5fef + - 7052257b-849f-4994-8f4a-74c19d894315 + - 118e668e-e4d0-4b76-bb87-7f111d92490b + - 1f0a3659-be73-48c8-a326-04692dfadcd2 + - fec7d5c1-1393-4ca0-a8fb-c6b59fae6e5c + - 66fab195-aaa1-4030-9fbc-19415ddfbd44 + - 471b228f-500c-4f80-ad38-36ac827b639c + - 85989d78-4320-46a6-9743-61e5b24442eb + - b93a4ce5-0a17-4950-b8aa-0519b0d308c8 From 22dfece9b10b266cf7e9c29308ee107db357f8ee Mon Sep 17 00:00:00 2001 From: c-suvamsa Date: Thu, 15 Oct 2026 19:37:42 +0530 Subject: [PATCH 2/2] Move v1 result into main leaderboard entries --- .../{v1 => }/entries/2026-10-14__claude-code__claude-opus-5.yaml | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename leaderboard/{v1 => }/entries/2026-10-14__claude-code__claude-opus-5.yaml (100%) diff --git a/leaderboard/v1/entries/2026-10-14__claude-code__claude-opus-5.yaml b/leaderboard/entries/2026-10-14__claude-code__claude-opus-5.yaml similarity index 100% rename from leaderboard/v1/entries/2026-10-14__claude-code__claude-opus-5.yaml rename to leaderboard/entries/2026-10-14__claude-code__claude-opus-5.yaml