diff --git a/leaderboard/entries/2026-10-16__computer__glm-5-3.yaml b/leaderboard/entries/2026-10-16__computer__glm-5-3.yaml new file mode 100644 index 0000000..83a5345 --- /dev/null +++ b/leaderboard/entries/2026-10-16__computer__glm-5-3.yaml @@ -0,0 +1,169 @@ +# DevRev Computer / GLM 5.3 +# Source job: 003cd987-31bf-4ac5-ab54-551a743c977b +# https://hub.harborframework.com/jobs/003cd987-31bf-4ac5-ab54-551a743c977b +# SDK-reported cost summed across all trials; not a gateway invoice. +rows: +- metadata: + agent_display_name: DevRev Computer + model_display_name: GLM 5.3 + agent_org_display_name: DevRev + model_org_display_name: Z.ai + metrics: + accuracy: 92.86 + display_accuracy: 92.9% + uncached_input_tokens: 8980284 + cached_input_tokens: 33595486 + output_tokens: 943749 + total_tokens: 43519519 + avg_trial_duration_sec: 197.58 + pass_at_2: 0.9952 + 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: 85.55 + display_total_cost_usd: $85.55 + status: display + trial_ids: + - 3556a55c-29a1-481e-a519-8ea24d317417 + - 1802f0d9-27de-45b2-9cbc-981f6cccc2c9 + - c5b4185e-9ccb-4e8a-8f6f-846007f31718 + - 193428ef-927a-4abb-8bfd-874dc3cf629a + - cc3b0c45-f3b2-4c5b-946d-1a2e75f4a087 + - 582ee50d-a257-4a5d-869c-75ffd0021b68 + - 7792d4b1-e0b9-40c1-b8e5-03aceb4ea5c2 + - a7547547-a08b-4071-942c-825f37a06aa2 + - fdee9ee6-04bd-4025-a34f-b51ac7522f23 + - dce26dca-b200-4e1b-afec-741c97d327cf + - 53d3dda0-c738-4a51-9710-3942dfbaa72b + - 7876537c-79da-4cfc-a0db-216b305a5c0b + - ef5c1ef9-7820-4d0a-9d00-d89cc2d8ff6d + - cddc4df1-30e1-4b57-90e0-f3496c6567b8 + - cc775565-e20b-48c1-ab84-096c4e6d9a1e + - a142bb20-08d1-4c55-b097-27c98967c47c + - 1e51f576-af84-4b39-9265-ef11cc2ec74d + - a05d0de7-4fca-43de-bb6a-d144fcd63d2c + - 1d994aa3-8ce5-4766-8b65-cf464e234e25 + - 4acfe249-3fdb-4a86-92c1-352b70fef488 + - 6fccd6ed-3f5c-4273-8f9e-b7d78f087ff3 + - 8e35afb5-6642-4f68-862a-6575797f5e35 + - 4489f309-abfa-42e4-821c-2ee209523c63 + - 7102457f-07e0-4232-954c-5b9c56a98f15 + - 1112da1d-940e-4595-89d6-6f593b597f27 + - 30c16451-7c96-4cc9-a695-763394518710 + - f77c7318-9a02-427f-b3d5-a167cbe35329 + - 0e284c3b-00fe-4e2f-bb81-527860431105 + - f2ff44f9-d804-4b70-a829-731a1fe34b86 + - 1dd66b00-4eb2-40f6-a9dd-a9c2112c3af9 + - c29e30f1-1179-43d1-8cdc-a9cdf64f0b7d + - 504ef63c-f959-45f3-9ab4-fce5ca580309 + - d196d9c9-41e7-4813-a34e-7ea57baaac50 + - 7edb788c-9e4d-4a39-ba7b-1d390becb728 + - d87ec01d-20ff-42dc-957c-aee377c5eb6f + - d5ffc296-ec1f-4a23-8fb7-d8cdebd73f89 + - 2fc745a4-dbb0-453d-ba79-74670eac8a3d + - 293aaa05-3c52-490f-a904-9253b28d3fa7 + - a09a14c0-f480-4ed3-9749-623d5450db6f + - fd5c1a23-d8f6-4bb8-80ae-0c2af937602a + - 7141ed34-6956-41e2-b228-fce9d542f8b9 + - b0d80a23-60e7-4c99-a753-f25b643e2b2d + - 7f8ef785-3d63-4491-b4ab-fa81b1b612a6 + - a3f1e9b0-3afe-468f-a615-49dd971ec3a7 + - 817126b4-6ea2-45de-ba15-1130936a3e15 + - cb34ad7f-12d3-4cc6-a76c-50ecbe45b662 + - b8195870-f439-46ed-8581-af26d8bc297a + - bd871ba0-ab7e-488f-b161-a951fa608c98 + - d1e56b83-3c56-478f-a6e9-21ca904ed85a + - 004f9dee-e9f4-44d3-9ff7-e297da428364 + - 7ad402be-7a83-43e0-b496-861065400bc7 + - 3cbb0560-b476-4f28-a14c-435ca60cb735 + - f717796e-529c-4b2a-963d-09bc4866dcca + - bac2839b-45a7-45fd-b0a2-3bf3be3b1a38 + - d511b05e-dc8c-4856-8147-2f783bfce331 + - fb70dfc5-17ab-40da-9976-69442e7c4fc2 + - 9df31654-ec56-47eb-bd5b-9f274b1dd813 + - 43569c32-f27c-4941-9445-78e5ec6048d7 + - 5ca83a47-f402-4eaa-84f8-3b94eee11bac + - a93eec04-ec81-4b02-99ae-996cdb11469b + - 67742df4-07e5-4fa7-af07-a51628d8a1de + - 1aa9af09-a448-45c1-9dc6-7e312c113021 + - 46a21209-7c06-49c0-9b6e-9f7552567ab4 + - 38b5b97f-8284-415c-9a2e-e8ec96d6eff2 + - 282f8670-2ca5-4fb9-b711-a2c7992fabab + - 499a11f5-b0ee-4dba-879b-c439d8808eb5 + - 4ab6126e-8d1e-49c3-9ec2-4aac9bef2085 + - 463f1cd6-1205-4f4b-b5c3-994fcfa95fc3 + - 437380e7-a382-45aa-9f3e-155745002813 + - 663f4fca-367c-4828-a2f1-80e2b26eefdc + - 30fc225a-fb6c-4655-a3d6-12b4fd0059fb + - 293c78ae-51f1-4e3c-b1ed-33d64ecbb670 + - 56347c13-56ec-40fd-860d-ec80bf0b9e56 + - 1547cb96-5a2e-483a-a621-04eb0e79e675 + - 97c9c908-9271-44be-bc28-f7d5218ac4fd + - 1f04030f-39be-4879-8203-18a02d761645 + - 6b0d6d20-779b-431e-84bc-b476e80b1f6a + - 22f2c369-58fa-4b39-8b1e-4647e2e1a085 + - 937ce4b1-b20f-4b9a-af07-4ac61e8d2fed + - 0b4d1e15-c1b8-40e3-bdce-2964c803cf45 + - ba6a87c9-4977-41f9-a916-da6c18a4a689 + - 42c79232-256e-41db-adc5-1a3178c49573 + - 87e3cea8-8b1b-48f8-bfaa-6b40088decfd + - d1240a90-8953-4664-9655-10b5cc0d0902 + - e1458dcb-59c0-4f24-abeb-900f86426061 + - dc4544db-6580-4703-a40a-a134d4bed50b + - 7a445d7a-648b-4470-bf19-f1215a9369ea + - 80c3ee73-20b6-43d8-baa0-72f2a88a7b76 + - 9bce0d22-3967-420e-b22a-5af270228bbf + - 995354e2-db8b-49c8-822a-1eed9dd748a0 + - 4359f469-d3a5-4d6e-9af9-42ab81c45fae + - 5efd4999-b74e-413f-8416-d3365aa61634 + - f9aad4c1-45a6-4f2f-a3a7-af754505a982 + - 4103689b-a613-459f-83e8-09e27ec5f1ff + - d6d90e9d-7071-4dfa-b766-bb9046bf5a7b + - 33c7e09b-49a7-433c-9d0c-68a7a36205f8 + - b87dab61-4a72-407a-a968-8d2b598b0232 + - bfa6c908-df53-4623-8186-2e8f4f77c82e + - 25361ba9-8b32-4aff-b195-465b8055b80e + - 7f1c5c48-3017-4f8a-931d-e98a3a234438 + - e329b33e-c10d-4c8f-8df4-9a7ec06274d8 + - 40ed4344-8b37-47a4-b46b-d05d624b5ed7 + - 0cfe21a3-0416-4a9c-850e-86f02c74aee0 + - 24ff0843-179f-4d24-817e-cd4f3e68e58f + - eb140ce8-6219-494b-9a52-103fabb4fb70 + - 60fc1934-6cf3-45d3-ac43-da0af8063724 + - db97a8ac-dbe4-4947-8f4a-1d19591e3a37 + - 281b905b-00d1-4a23-ab07-4f75f34f4875 + - bc95afbf-8d88-4069-866e-130eec22a2a1 + - e5b7bb13-d240-4e04-96dd-4012286c8cf6 + - e3a5fa3a-7711-4dfe-b78f-c24000d4c206 + - 3ba671fb-b5d0-43d0-a03c-cf682a720b22 + - 82d269ef-4e12-4224-bc07-4cf8bc32ed79 + - aafac2e4-e95a-41d4-ae82-7eff6240ce4e + - 69ff4f43-7661-4e7e-be22-f5d9db9c1852 + - cd3f8c87-f034-42f5-8247-3b118ffd197a + - f0a19df2-a943-48b7-8aa1-8277a93e666a + - 7a8cbecb-3a92-48c1-89a7-1444fdc527f6 + - 45e4e025-1517-4654-955b-02af8d790514 + - 63a0a950-780d-4612-8bfe-87fd7d23e082 + - d70830e0-1b25-470f-94e9-0c25cfc5907f + - 35ee2a8d-ad23-470c-886b-7f781113f538 + - 86b3a4bf-c56c-42da-bc62-a2687898095d + - 181e8985-7c21-4d0d-b3f4-aab02848a6f4 + - 73b59c82-bb1a-423a-8d3d-2c13021b4ce1 + - 78c9904d-b0e7-49e5-9380-2f5ad61ec520 + - ff136707-68a1-481b-bb84-20de86fd62e8 + - 2c728ed2-dc63-4b9f-a656-b9f037a65e3a + - 92a1c8b8-ba60-4023-967b-71b6f2040b1a + - 46fb6037-26ee-42cc-bb2d-760827eda25e + - 35e811cc-30df-4da0-afe7-1295cbe78298 + - 3e2c33a7-2934-4e86-be4b-9b76735a4f77 + - d97e4630-d265-463e-84b5-df7abee2f2b5 + - 7fb4b90d-4fd3-4c29-ab15-e61fa6802d2e + - 1792fd3a-5f12-45f2-a21a-06cc020ee75c + - 4ce44002-33b9-449b-b3ba-20eeab658617 + - fe3fd9c6-fd21-4bc3-a988-576faf034b84 + - aad247e4-6db5-4237-a88f-c3b56bcc1f0f + - 269fb927-30b3-43ae-9aa4-91bda58d5c1a + - fba8fb7c-4189-4486-b150-e4d923e98bee