{"generation":"abc040eff04e454ebf8217fca6d72c18","objects":{"seo":"4c60da0369a6a7a356a5025759126210406fa4d9dc23b38f42a3fa0260755298","models":"c7d829b8f2ac97f739f7cf49a34874cba4fe8c40b6d2977e0e6605f38fe4f74d","benchmarks":"bbaacb759a8056635ef91ed91930d2ddeb03bd454702e72f730594b8f1216215","companies":"a5ef204f55b7e62b29c374e6f0712f43b5ebf14a5f6d2deefbd8275c6df929ce","stats":"55347b015c177d1e5ceaf902543d13ec7bf61b99ac97c78bddba679f1b4784d1","home-panels":"d0689a338badbd297223bf32e5f02fbd461133a93cb6378c73772a34e3b94fc0","redirects":"b0fec7b8bd53782757ab109aeb45d923b02f46dd85dfa0e2d98dd1e666248cc1","search-entities":"0622cc84d4b7eba498804a939a7f60054da62aa3647547bd78da83d17a8a63ea","search-relationships":"2730223c521c7de0bb68068144159165b545f4370c04465b25e10c5e525c7915","company:anthropic":"c40204196f82d81167ded75518a084630e6b9fb982aca67ad59a1674b759823a","company:cursor":"33812fdea098025efb0285052501fc04ec9f5a8110ecba23e136d8d4c2b7387e","company:deepseek":"f840e86a4e743919dbac6b65bd0a2cc40383c66f428721753b27d85d341ebc2a","company:google-deepmind":"01a6dc47574e27fa7483c8820bdb9fa44b890b2b542c2c721ddfccf0f0885738","company:meta-ai":"0b6cd5cebed7d4379a785efefbeaad3022d1da922990d3d86a5e4743447b4d42","company:microsoft-ai":"923d473dfbc6d33de8b1810bf83921f7c1d9875b3965f807cc845808d3e1435a","company:minimax":"ce877b7c1541f976a3aa7ba9dbe65aee9415f401ed5e10da39bf639fc5e24be9","company:mistral":"bd670b52ae065477a94f06797e9f5252d7ce90115165bb74be45434894c8943a","company:moonshot-ai":"38fc6e370bfa0dfb3544b919f5b93296a3fcbb38381ef99969e4036339c7bf0c","company:nvidia":"6c008572bec7349b8572bbbb12b9682cbba86d9d55149b8cfdc26df782587071","company:openai":"96bb6da0a97063b17280792cd4d208a45223834b432b7090167f0de4ea900e1f","company:spacexai":"ec46e8e2f58b8255584d897686eb431f3be4ce66662f5832f907f29f180239b9","company:thinking-machines":"0ce558a3c8b500b349b6b9c43b20483131161a6bc13ce3d47d5b358acbed931b","company:tongyi":"54cb2d13140bfa27887462b0c9da62f4b13322842a9f156a7d84614f6e23d104","company:z-ai":"519f00ecef6b78094c6a3d1b2520dafc25d65f08e6f5026551ca072d18bb170b","family:agents-last-exam":"ebd307c9dde8853837890b575b0a837a794cca40dfad472c63bb53545b737208","family:ai2d":"b3fbe7b238bd71ff54632cfcccfbd2356bde55d9108abd883ae3cf015b1e2c0b","family:apex-agents":"67d4156f17a3a65b3b51b22349bda73f4e0865ba86a4344da602229abd40514d","family:arena-text":"12f1836d2b8661d3bde8993b4557b244a213cb8b6b73d360cfbddbdfb8f675d6","family:automationbench":"889b5ca8de62b946c75812cc9b6798df3a172806a400e76d490c5319a917756e","family:babyvision":"deb79a8e405cb32d5bc4909f4d8791b21b9e059911841e9d2af5fd66d12255ee","family:benchcad":"e81a9c44bd2af8f8fe1edd64713aa68c0dcd0c3b56082df67fc0d94816300126","family:beyond-aime":"4419c33545d6336ee3853cd8e3ad6a35cff364e35c168087c1bb175bc95d05ae","family:big-bench-extra-hard":"68a04985cf5489af03266cb034053dc7bf1ed5171d6fe770fda7400c1b825e9c","family:browsecomp":"97c114ae4531f419ee2ea1dbd111d30d19ecc14ee523b66c2b0fa81492dd8b55","family:chartography":"2941934065a7008cf9268adbd9afeaae5e5d3a848eb642def6bb7082f2840a30","family:chartqa":"1f43a777ec32bec3e57e6bffe8eb6bf26451b715bd4ca3ddb22a430e9d63411f","family:charxiv":"e0d60630789b64f9489b32b3fc4c30d4bc0f0b3d382916e3693da061d2e1f77d","family:cl-bench":"0c400d4be14a6d4bfc162d44cd450094d5b92e32ee3fcb07accd17e2f902d47d","family:codeforces":"01bc8fd9ce95552e54db5a4e5935f6641b18b593b7e2fb4418da85aad8ad96e4","family:coronavirus-ace2-cell-entry-screen":"da157cc1f924be2e6a7eead50d9e6bf00fb86e2d0f3eab83897f789adcf39e92","family:cursorbench":"86ced86deb0f1e1888895dc99ea39b9356ddc70fd83f5be48a6542e0ba6c34e2","family:cwe-bench":"0b24932a0804a2120580d3590b45692ea5784cd92c2f1454535a50728e4dbf9f","family:cybergym":"bbd5bc433fd0e8dfe78db80f710706d825f21918b485d140841e18ba79cb8324","family:deep-swe":"880c4e3099bc2a21ec10945bda1a83e1d333370aff7ba7d2a1477fa0f385c64e","family:deepsearchqa":"e93ac5c6026c680cc63212bb7cb3aa42dd73f18118040e1159e6bdfdba6a19fb","family:erqa":"24e72458103045b9b9ab1a3bcca5601dc1d1a3c54ba60c700d47076d28cce321","family:finance-agent":"04557c00585c012e3f1bd2515ada95f31e6eba1b2cca84d864633c9b9bd36921","family:frontierscience":"04dd9e50e8b1687719e94092748e33348cc5db61c4458c9f2675bfad75c8506f","family:frontierswe":"ab3c9c39f9ac7c4cf9bd1d8114adfecda418e67fa4aebe51966c86441e118a39","family:gaia2":"bee1aee88b2da44bfc18d16d83d06fc47edbdfc0829629a547c35f2501546aa1","family:gdp-pdf":"1a29f7474ddb491ef570c803dfa0969644329b6f286acbec25391182c2c002c7","family:gdpval":"da3fb239b805834759d24ed34385fff4da9d0cb2888042d303e9342d5fa732bf","family:global-mmlu":"38094a0c6a1913d520cdd6b09195a1fce6f34978db07de79ad21e6cf488fe2db","family:gpqa":"f2a57f293e2837e124fc8d2d17beae0281d3168193353a86563125a7ae797321","family:graphwalks":"83d5f042d08913e3368a6ca7f5aa3ba1df0d7a9371f910458d0e8a606ed4de8e","family:hallusionbench":"08016ec49763574660c7e0d3a8864a958b74a878340461b050b7cdf6187b0036","family:harveys-legal-agent-benchmark":"bcebc60cfad9670e6e522e202f92eda5d2cf551d84019656fcef6084a778e0b5","family:healthbench":"5b6801e4ef5eba8818ef697d7fc555f35a61ecb43fb64df3b1d8c79d3900d3e6","family:hle-verified":"5c265a960cb7228f70dc4fabe89534f723248ee5533faff8778e4df4ed20a4aa","family:humanitys-last-exam":"fc858be1effb6f4b025c82c3502c4e0000198d63a4d5eb66a9155531c7355cf9","family:ifbench":"d23c059b0b735e7e5f5577864590446013917c80b5da3968918bfebe6f1e65a2","family:ifeval":"a6118d5cf6f3e453efa14033e3d1b58757c6af1bc5b4e2d0b4d6942d5e139355","family:ipho":"ad6225ef3485e360c768f9aca25b33c97fbf079853c951d4c5f1ebe7158991f3","family:jobbench":"8cd1c3329972eb229cdfce798ebbb6fef6b49c2ef8385f58eebf21648b7a24cd","family:labbench2":"0d95b8fdded6e638cc632e50bca31fbab6732204d248795324f26819b5e99033","family:longbench":"7a03938f0eeec616908a66254b5c972363c63ab8a8d5c1bc28a72c4f3b2a9a85","family:lvbench":"7e71911508c8df64eef526c8530caa459281d396b5c522639ed371a16db99eb4","family:math-vision":"ac4bb1a0777619c3c6f351dec79796fe7807828a38be58267bf505841723116d","family:mathverse":"5e94271d2268b100042eeab47d218e931c0080043cdca4a83f918a85605c7963","family:mathvista":"43456bf93006fd4fe86ad2e4fb60d2ccca866187066ace7f524c34b5436f0cbc","family:mcp-atlas":"7090f32c8fe117ebfc5db34d0c946e22141b64701f65fa0e8b78990465e60cc9","family:medxpertqa":"dca67543d5016ddaa1a90003045823141af56fcc66d78a78f531493609b80a47","family:milu":"ea44f8b74e3a8793657110f6852e8daa4307975862333d5edc00ea3dd4c606fe","family:mmlu":"57c4a8cd764300108274a0ebc3cd15f178fcbbab7feafedd07a8fc3574d61e3d","family:mmlu-pro":"455bff323e86e84154561a63682986ff175cf000c913809e577d8e33e60f1bc5","family:mmmlu":"9e55380050918ee5424075d8d3c05306a109a0190000b0dcb75dbbbb72996535","family:mmmu":"326363d0a7db8059eb73f4a663392fccc7d5316a173d21cb36d1c2708bbb6727","family:mmmu-pro":"8c86f41d97b6f5244ba11ee3d99dfae034a714462bd9c80c815279dd9b4403c5","family:mmstar":"5652fdf4961388089dadf3fe7541ad46b4509d95e1d5db8e99c195b28d4dc066","family:mrcr":"8bf65a5c9c9f8491cc1505480ba7e4e94b728418c9221c1fd01564b4bd4445e3","family:mtvqa":"6f07c09d245671e6bf341ee5bff5b1e3c854c1387736521632ab1924be32650a","family:multi-swe-bench":"7e63f3862ab48f0484beda76d741c1b6797a66d509915bd6e47f25d4446ea1d7","family:nl2repo":"abcd48e5263d5f8fd766e37db80588d239b531dc0cfd73f1616f517fa99685ce","family:ocrbench":"5113c131b26fd4459aad0ec83929aae3ade4bf13442cc3293210d6ef85e200ed","family:osworld":"03ae7b7552f8bf26c3931c93554ef71f9ec891213a5c20358c7a30767e58bc92","family:paperbench":"26766443ffb8171319073cb22e67837002368740ffd3fb8e2c406ee17dcac707","family:perceptionbench":"35c37a6a16b3d628f53716a92b8e45c6e5a73a28dd05fe59fb06d81b00862645","family:phage-plasmid-co-evolution":"34ce49181fac30562e5bb3c53c172fa2ec9b1f4f876a75761a7eebf40ffbc4bb","family:posttrainbench":"42ace215b0983123416c5e1193625743cb97174ae66cd0399c3d4700243d5d4e","family:realworldqa":"0c069665e8a684d4e5deee3933ef26a3bd5fb43ad121e08fcc70e98cb098c0d4","family:riemann-bench":"30f8da94f945d25c5fdcc2ad3288ed0d50dd83ab62988fb66961af185d7f7d7c","family:scicode":"e7b8f44cb673b5d88588a25520d5b1ba5e00e936407df432c7fb628e07a036b1","family:screenspot-pro":"25b4ea963a63f32ac6efe2efb7fbfd07317df91d275fef34797a83d22aa41511","family:shp2-protein-function-prediction":"a04d2ad04843c0424ae9653abbc56cef5a3d039d5647235c23ef4e9871d5e68b","family:simpleqa-verified":"67e2671c5416320d0ec10defaf7e012423ccf81e861656d5c30d2fbe1055fe0e","family:skillsbench":"146f259a82b9dac5966ac3f50e216c5243dff76497b9cab640e675500467db98","family:spatialbench":"18fd1e4aa1620d26e49a01157288affd15b70e13472b60ecd122e7a8c1755c3e","family:strongreject":"a08b57b3401eefc1cc30696f4e554328929eb22ea596d46ce65add6b1d05fa38","family:swe-atlas":"80393d50b0e8b63936708017968d2a69b4286d22f93a69b2ae3d9552ef256422","family:swe-bench":"004be0c3fb5b8838e9789e7f861ba3a14a5c9e0f41139c5f9cf383bad1db2110","family:swe-bench-pro":"5c5a90a7e10ec23bb214cea19622703c391684aad56dc5fcf773abd18c3bc8e0","family:swe-fficiency":"d4cf7621624a6a158fa125266f7d8e044613f2b8f53c8edc0080fc808d19fd9c","family:tau3-bench":"51c5dd2f3b4a12db14fcb6d62cc3a9a162e0bfab0a4d48bdad4f6b0d39f382cb","family:terminal-bench":"603eae7fee273f2b815d1643aae1f2f9d8844360b216dacb36100509881649fe","family:toolathlon":"6599d6500f9acc8faa6b37d72807b9a0ae212c98e0b97f8b4472d51b99396cac","family:vals-index":"76a05e7300439750a31fc145c8258e6297189bb64f89f378db4c61ba2ad282d5","family:vibe-code-bench":"e66bb7189c38ce84c31a05d239f060e4e98071e89f11facf279b435a2341ba89","family:video-mme":"fcf995033d1098113e35ee1ac82d37809e6389d5ca8f4a8f9697fcf134ce608d","model:10001":"db62f7a8ff15c050d2fb19c5ca246ecf0846111ab21df5249718b686dd33c5d8","model:10002":"46a0cf6fbe88860afeda5568a7f2da5c17ce1ac72ae9588d8e80f3f288566343","model:10003":"f49a38b5728a9bd1e7a29283e643fbdaa59b0e5e7b25cf4d49986ed432e3a2ab","model:10004":"d024849942fd5fe1557a8c539f1f408dc7d9cc8764f2f697fdc1cfd07499e978","model:10005":"5b6f3f676a81d6aeaba812ef77a1ed89ad84674aca324dfefc160b6d056e44e6","model:10006":"cb9011f237a51de116a13d7dae2394ee16a215bf4fd440ad76dc078e5385c376","model:10007":"857ee93dfd19887fe46b307793729f65ce044d96f9ba4caf8729a53acc3d3a5c","model:10008":"d53ded38c6d034d7acf9eed159d94563ed400a2b4b9858ea0465c9d9abbbee5a","model:10009":"a83c202e1219aa75cf78ac32e2a0b89ba35cdeb52382aca0325c9afca359cf16","model:10010":"85b58a7c2f848574a3154462379806854c2e9ccbf17b8ea321c12a39c28495ae","model:10011":"f93c85007454c248798f665a9a3348d7b211e6379c68bde796d7fd40e29ba618","model:10012":"9855b8e659557f61af2a53175b962f39a1f3b75ef355b6203bc667c9e5eb19f4","model:10013":"eec49e5efb6d508441e5242abc1ef9723bf6ecba776f68dd20f71e4bc93c9851","model:10014":"9052cc60f541be2cf7db67929fc05cb7f06f768591db705dff08e73969cf03f8","model:10015":"dd3556c8135dc4b819093f6ae4a5b5ae700794ace6e52e893b617fac42b331b5","model:10016":"9ad7e9de87305c0f6b1303e1b8f4b0392d7554aa663c811d71abd936484bd6ed","model:10017":"087d8486e42b12c4deb16fe6f7b91e68ed232657c6f73c57a6e5edc8ef6314b2","model:10018":"7ace580c877eb7ef444587c08e3068ecb502ae258f1f071be936313d6c323642","model:10019":"7ec3b4aacc1624686fcd09b9de9ab1894e7b0f04e81d291b57f33925ae92b3a2","model:10020":"0853f1b52700619826ef05bb7b11b173acfc4ab8722df74721dd72100f2c9c56","model:10021":"0b9ee7c68bf1953f87938ec61bb72c48fe796a53d2f6cf31336cd06daca153ba","model:10022":"4d9043991313ade0a962d02f227198d439dd698e5d06962cdeb8b6e843c8eb27","model:110001":"4e66df0fdc00b62516fa407799bedb4886a249b86d25615f32b5905529410102","model:110002":"3099b129f5ce18a2a6437c7e0d44f50db7c55ca3e04a8d705dbd6d689d266aa7","model:110003":"b9b0f3340e7b3488fd6ac4f2d068044e7230b8060b8b9434168e800364c3e77a","model:120001":"25e0e62f59f66780e346339254bfef2bfdb1b2cb1c8d87133a67e3de9e5c0c56","model:120002":"89cd5604b3b08d509c39376d95609fe485c9152e5602b71362a2e3904faccd0d","model:120003":"3b5dcb107ac6589bf96c017496a918518574bb95796f404f941f46ba24a43857","model:130001":"1a5baa96cc213f3b0caaed905ee88e91db32bfbf4530ed75ba3d7e358d4482f4","model:130002":"b50e811e55cf32017db1ffbb66cf0ab6c7f126d060f7cb2f06dbe40243483c07","model:130003":"fd880007fae6b71a997365fdec8681ff64fdf305da5e8043a19ab6c484e425a7","model:130004":"4123e7045733be100a8adec862553951cae4922a1d50ec3db1194bfb155610c9","model:130005":"964304fb6086e44c93d51376037b389d22ab1607ee161c4861b650b0b0c5c848","model:130006":"65e5f6ea238bd899ad839a32a359c7797ffc1f7713ee9628b9c447eafce54974","model:130007":"6c7a501b0a1ea710b47837d2dab3b0f5e2f3246228108a465121c4ef1fde3842","model:130008":"36aa3f770805505f7da5191479fd6e40762233db551fd73cf775d1da2dd0a1f8","model:140001":"47c52490307ee551f47683b9eb8d29598f0f3b94f88bf3d67ab40d1439a34c54","model:140002":"009fdb2547cf44d1c333f8bda0c3be2d6fb0b9c87ab424b6aac70ae580de028a","model:140003":"3e2b3e5fe91653a8fce33c5ac87b68377b17f362064ce5b9fbf1922e98b60234","model:140004":"66a8507e9d7446f2765003c657ea4b04c7ffb8b79f60d31d0df5dab4ae0bea59","model:150001":"1a2ec174fc7f7ab220670b923394b13908f9c8e69e016c96271a135adcae4c51","model:150002":"42b8a8a9213a2657fe31b3ec0aa55716271462844e0f24b3e0c545679c68d343","model:150003":"124c30e0d98f50b127a9de8b0b81d0ecdc7f0f262465050e23fdbe768011adab","model:150004":"4dde0794ffd3b2a97cb17c1e551070c55f9d1f657be7e59c5175ae1870f8a5c3","model:150005":"4ea137806bf7e13f0364e368febc535a8b02ccf8ece5bbb0c4fdfdd2be90836a","model:150006":"f8c1b249379ba3f082b578867f1cadf448399ff964503b4771e2f59210227d0b","model:150007":"c16a0c4d752883c3e22e1325162790fb14a4f82e25b6f01bee2ddc1fa4889834","model:150008":"ace5a6db7583d08caacf6ce5329725df8dcd4573ed1f7fd1874ce7f22df8f6e7","model:150009":"27a015463f36657340792d7493205c4c8e3177ad129d3b9be540d56261e54739","model:15001":"c0210ebc5db40e267dbab9f06f49e260810329003212e0a2639452aa64d639f3","model:160001":"c80a4405e3c82d92e3360b8e253b12f7bc7e4de4aa51da98cc7d4b75807a7214","model:160002":"9bed4fa2005225c41ba88b6d3ffdacb413cd8570aeea374d4e32efa048448617","model:20001":"1760085eaa71383dd81f1bcf339945a77a70d6af601d085444c6a0fa3f5fcd61","model:20002":"f90b8734306177b578434ee776371282774165b662c1e4ec2300aee94fedd236","model:20003":"372f75becd123cce45ce3097682067bd36ca92d79bcc47feb034f4a14710f427","model:20004":"080abc28ae96f1e927a92fbfac37758015207d19a260cf42fed888303ebc19b4","model:20005":"57733c5db44a475e8b4d077a572dc9847d57d24c5a7ba5a4ec5adbbd90ec493f","model:20006":"b02a7e9a75465dd4789719b5cb3824416a1b4ebbd19eda393ec4d03b73007b65","model:20007":"2eaa835700606e460181638508b7e8021ee7d88bd90b7d1f84b2a76dc2dc773c","model:20008":"d31a3fca2e86fe5d9a0fc7f1616960f015114753f525a07e973909def3b271e3","model:20009":"b2c36b4ab899bb2229f5f6c78e4c59b08e1ada8b1ed062daf3e79a8faf37612b","model:20010":"4b1dc146882454879827ee02598884c4b87876ffc26ebd8e67cee8952284151d","model:20011":"407b87017cec8bec9b0f5d26519bc543e0ba3fb765121f7b94422fb82f7edbbb","model:20012":"fbd1e83470e41b8f25f212402f86cc46a59abbbb4f0eb65ff066985c423e2c10","model:20013":"2a4a5a55243a3dfb299930098c9422bebb91aba9f04599eae4ba7aa45c337da1","model:20014":"b80c727671dff15b5c4b329989662c625acac5be86093f0a2314e1b19f43267c","model:20015":"fef380fcb6a5448702d7a7f67892275055454ef839fc23def0247ec5c51a170f","model:20016":"67492b90d33a6f72c9e5cdc92d0957fcfafd529b6668d21c0eea151a48ffa15f","model:20017":"5848655b847333a510079c79718b9a28b084d04e135dd77c7887f479ecd40119","model:20018":"8222f3755ec4e46a1633cb7ef0eac1e1107a34fc38d13cb3912d61c39464a523","model:30001":"09e92116c2e7e2e69838ead35727a060bd997d76b23872afcea6889a776cfc66","model:30002":"765c7f26e73baaa9ec47c6c5cfc4c588d4b2c08db082b60b955f35cb5f15ac7f","model:30003":"59c3da01d946a77ebffb10050e3302cdba1dcfd3549c3a14ce8a6737659c1aeb","model:30004":"3f5e8a8684fa1d5ed7d95cefc2549cc59ccf330fd13aa40a6e3932088f55d063","model:30005":"12634ba406fd547ad169439c13dadaf86bd9bc3c701449615c1afe6d40df9140","model:30006":"9ebc0ce0e541f86202e0c5e14d9aac3df5cdfd04794b1170c7ee1e02aca5d66d","model:30007":"320340513a2b4cc7efc8c39e1c02d3b1ec5cb37eb353491099c06488dfd3529c","model:30008":"2ba3f113fd55ce6643073e2efc9163c0e58fed4bb7dbbca02ebcf7ed883ee2f6","model:30009":"5a7b71157d03badd94daa07f533a0e908d052280b9936b96962e39ffaefc0da2","model:30010":"bb34ef05fa5ad1697bf6c2a9b3e58d6ab070589552d54848d2ba5f56e8f82f74","model:30011":"9fdf7553bd664161b5596bf578d4b560a6872c067cbae75b9350e71aa20dd763","model:35001":"1a94970fa48399f7b988e23d8a6825882949d59070bd3734945454011914aac0","model:35002":"69faf06017a12062293190b01ee93fafcc537636b9c99c2de6349c046183a292","model:35003":"08e909e3d18ad61773b6f1f2239b3ca845bbb96e1efdb6c40085421e4688e1eb","model:35004":"ec4926c778f85097cccc1860168c798988e36c67e6ef927726d5c8721a5c0265","model:35005":"b2cbe08b72881b5fa0b6c9553f043a5126fd795f69a047c33105c5bf2f58540f","model:40001":"3d948e3a36c39db92ff5f19276090eef4aa720af51c2dfff079ae77b28e9c756","model:40002":"a749b7c95826c92e66fba973fa2a279242cdf5f1c9194f36bb0f95cba3acdbab","model:40003":"6a0219c1b7e90f0ab2b659ccee785710db43dbac3a4f0c41cee5d4978a4ec572","model:40004":"d75732963586984a145bd3a2247ce6b4cb9440feddd2ee2d725a6b17c38a26bd","model:50001":"1e3abd144c4674af30a4401bae15037f59982160f2374af401c5418a16d96b65","model:50002":"e0e019e1e3a23f38a960b58d46f9d0a42fd519c75492308014c1e927c91b15fc","model:50003":"bcd64a1d37d56ebc87b0930ac2eec1923d6b81471e5b1fd2d99d2d25f0ef8df9","model:50004":"a7a771f259c93bdfb8950c4f72c265fe0cf5e79ba8ae5dea0a1e8b425b83375d","model:60001":"73b63a5ce40a780edba242bfd194bfd38abdb19221e83ddd9538f25e85010f99","model:60002":"05c72ce666bbd483634cb0046e02997e4b5bca204342a9944867d99cbc96c6af","model:60003":"6e1dfce092880b28aad5a6401db5576e967bb27147259e80335403a9e2ea1c2f","model:70001":"4a2ca629d1988cb240910fd23355e2f05ffc6f11670ae8fe6af81a4a7ccf28c1","model:70002":"048cc185735c6319f9cac79d74f13d32a152ab4a0a3660073b7acc70e34ff208","model:70003":"9b3e1d9b2beba7a8489d396578b773fcf1996537b4c205ec1295f4d1b0a44288","model:80001":"55ab4dc6f489656a6e6c537c189541388473894aa513a7760e5f60942e74da0b","model:80002":"807c65e0ff954a08faf13d0127927ffd876ba3e0eb7ecf8dfa9e85bb7a0c9f38","model:80003":"7758815d1dbf0fad99efb1859a27038a07eeceb7da6337a515a7b6f6105517f1","model:80004":"5eb5b48ca245112011c027194204c1195b0d367895299b2dff2eb083878809b3","model:80005":"0180deb0bbc12b847fe2afbdba02dd353b9ce7349ed5fc28cef3254f20b8b6f4","model:90001":"bbcdd18b044a010ed9680b0c0c88a55107e96756360c92a868639eb8ab0fcc85","model:90002":"c2afc9fc4f6481c8259d122a03ff2dedfaaaf1dc512be1b040c1e65f5bd82d63","model:90003":"995a508d0a1a16e759cc480ec8af54b299614f26e3091072c4732c01c6cdfb7d","model:90004":"b9da2432a6ea321dcc246b7f3f1979ee1bb46e6dfd4f0e8972d9193da12a91f2","model:90005":"7e35fc764caeac0b134a366f86d3bf9e2a65036260614325d095ace29af190e2","version:agents-last-exam:ale-v1-ale-claw-5h":"2fc94c3db9617320be7a7a257499bc6486d591060542e43394dc2db258b87477","version:ai2d:test":"f51cf1cb2235d5e28a1129d052cd25c30826e217647678f160c4785e2c796831","version:apex-agents:original":"a1fe7f8acf920144813ed7af0ddfa09cffe32b4439d0d98bef8664638f1b282a","version:arena-text:text-overall-2026-09-13":"3e89f7b56320e7b7563f01278e9765ec1d5bb9f2023ea9f1eb3a4e7b3f036c67","version:automationbench:1-0-6":"490947035b44151ea0ded0fbce03050dc184b2b849dd1db1c968b93470eec068","version:babyvision:original":"bbdd478ce22d1c65e2bc98815cd138f38f01aeb62475e8483d44cc6b5454fdea","version:babyvision:original-python-enabled":"473ea9f0b669722f749733cb36d6f63b5a04dbed250924f54dfbeee423b6258f","version:benchcad:vision2code-with-tools":"3be32cc9572985d60152df13cc7be4b8d5a4db7f0416cdada3b33750c695d7ab","version:beyond-aime:original":"c580a89b8745bd9ad4760a7f85a8d71404a3dfc245296f6081a61a75698a6f58","version:big-bench-extra-hard:original-micro-average":"ebcc79944cb3e9a33df1f08de20302edcb732fea52881b969e6ed1098d25c25f","version:browsecomp:130-question-subset-mercor":"950008a1176deec761cc12315350d354cc74226942bd2d82810c3c4b39480da9","version:browsecomp:browsecomp":"818e98cd2abcbe9a177fcd075efd1708285b814488377d5f654015bf34383bd8","version:browsecomp:context-management-minimax-m25":"97b94b4b9126a40956cf5e1c16c62b733816c4b7bbbf00a1503bdebebf9938ce","version:browsecomp:with-context-management-inkling":"070cb576c5d5cf902e0b11d897d3f804daca17a4d42db5de25f295968fdd0b73","version:chartography:no-tools-september-2026":"a7eb2a6e52a9ec56d2663e86fd651bfdc8e593eee5259566853a3d78fb138219","version:chartography:october-2026":"f8bcb7657c043edc1a72da8a45c5b9e511bebf14801cdd54235229e0f81f4273","version:chartqa:test":"4732a963cca859a7c0a8f8ec0b5366de19b52afa13712f5bba1a48a580037cd1","version:charxiv:descriptive-reasoning-mercor":"8ea2a80bf58f6fd3a0627e326c62a6347ea6787490885ff91434be17aecdd5f7","version:charxiv:reasoning-no-tools":"5d3dfa94f592e18e4fc377f4cc1b52914e1381e94156ff30615e409045aaef3b","version:charxiv:reasoning-python-enabled":"26cce2f48449ece59f51caa7ca9564976dbfd1809bbb255f18aeb0d660800866","version:charxiv:reasoning-search-code-execution":"9df57945cac3556966b3884a95fc1fa01b0dc252fee1cba4eb9e629eb27f1f9d","version:cl-bench:original":"7bc1f1ba1ca07d9885695808826d897c66c85fff16b75964cbed37227ab4d638","version:codeforces:no-tools":"6df90eeadc70712eaf56d0c563eb6c8b627cdefa201292c81110dc8d242c55a3","version:codeforces:with-tools":"441fbd106e277b2ad0dfb541b61a0c91a1dc3e8605015e2b01d12337037d79d7","version:coronavirus-ace2-cell-entry-screen:original":"edfb8675f2d8cbf7632c2f010777b5ff15c620c83c7ef4cf260261aa8f2b1f71","version:cursorbench:3.0":"85c8b1af9469ded6efbcc49ee66c1835b6c59fd78cb90f2b5049e31f9b34b56e","version:cursorbench:3.1":"3b5afe8fd79b05c99fbe8580a7f5e5562dfaf0b41aaf757164abcd86d4f2b179","version:cursorbench:3.2.0":"b02138e7aea4d585cd07118915972c569f0be5b5947fd19b14c7bdfb66bdad79","version:cursorbench:4-0":"f7a2350c2663acb45e167976ec190508da5eb1789e7d470a086dc0f4fff3e491","version:cwe-bench:1":"0a46a8e132501107e354850eaa0a9abef8344eab5db2e8347032dc339be5fdac","version:cwe-bench:1-claude-code":"55175c4db198881e05862931508f3a446bf4b05200c6980d9b0d821a1c9b19d1","version:cwe-bench:1-codex":"31d2e503dbb76e2344fc276e37ab5e2f9a40ea6fe5b8fbe4f341797ab74780c6","version:cwe-bench:1-opencode":"c52ea101c0e88ef0a7b684ea927ef4d8e44320248f183311c6bb527fc5ef48af","version:cybergym:original":"7da25cf5514993af793a96d9eda9d6206fd2280f3a47bb3a36ebf7b2ae3ad1ee","version:deep-swe:1.1":"f24638c862d439f28a87238ab822b19674c506e2a0c35f0c797858559e68ecab","version:deep-swe:1.1-mercor-mini-swe-agent":"7a25f1bf06781fde3051ddb6ceba86e71dcf089956654406f901e0387a4a6150","version:deep-swe:1.1-mini-swe-agent":"ade303e50d8b2bfa79e6c3f0a51b890afdd670b9aa4bde5b415e1ae9450fcbce","version:deep-swe:1.1-muse-code":"10a695dac4ec142339d5b596e3728304d222ae36cb33735154837ac31dec73bb","version:deepsearchqa:900-prompt":"77d0b4644ebda3f26257a6e731e096d8e5a0e7acc1354094b1e0eedbafd63fb9","version:erqa:no-tools":"a1aab99600af026ba534a5107565840221af392c3e0511cd862a705ee1041902","version:erqa:with-python":"0a378c3b672fe2545fb53652ebcdc56c5e2170837aa930b9427990d3d159a8cd","version:finance-agent:2-october-2026":"1e67ae79b50d9b94d18c3811111dead38bc19166841e1e74ca9d0fc11f337e9e","version:finance-agent:2-september-2026":"53d295de43c3b68a9d87f24e3f8aabad23a524b5f83e573b33bcc66b8b53c434","version:frontierscience:research":"9539f7cada9a6495f8dd006fdcea06b33f1ba15b1ef248b01d923ae637d48fb1","version:frontierswe:2-october-2026":"4163a67dac681d2f8e6f690d238e28e36ad119a95e7b142b02e97cbb1e6052a1","version:frontierswe:2-september-2026":"e29e0a1dd11863a52809535b56045d6cc501830ac8abd3f85f8f4f95f90c0ed8","version:gaia2:public-800-tasks":"f8ac534caf79ed2e0c588ca37f614f47cf16cd7f300e46f44910b76eaa7b5bc5","version:gdp-pdf:gdp.pdf":"69a6b9eddd889778602d8583a75f7830f0068286f59100bf38afbff8479f5180","version:gdpval:gdpval":"d09d3ae50c8da98b5cf2de2cae4d495a3c6a72d88561824a402d5002c7c963dc","version:global-mmlu:original":"e1be12364b5c45594b2b62ee84127c32830bdaecd82c653b682f2daa5f39b5cf","version:gpqa:diamond":"5ac739f95fea0c45e43262f0b182082923401e611ff2f118dcf3ff3fb0e571cd","version:gpqa:diamond-epoch-ai":"a58038824ef6d723bc51114513feae70e48122fca8e3c9788820d4b84608bffd","version:gpqa:diamond-mercor":"560726d7b3fbe024f9929f48efe9723609bbee611f71083f5f2344292dd9a743","version:gpqa:diamond-vals-ai":"481f6f999334269bbd11402e3d0cf10abbe710d8e76d837626130d3c219b2135","version:graphwalks:256k-to-1m-bfs-200":"c6f0ce8a9e59593bcd4f475718465bb40ff19ff34c3ccdd6397f3020a4200da4","version:graphwalks:up-to-128k-bfs-650":"4c3589698a72f805728971d1e0b50c6320777afe2acea016cafeb32e4e9f82b7","version:hallusionbench:original":"cd25a4b165ae39341519aea87c4b2c5e850971e69d7e2d981fff53d36c7c8f2d","version:harveys-legal-agent-benchmark:october-2026":"2c706289637136016203731c0d617384f585f4e80d2730c49b7eb3e8b9bac8f9","version:harveys-legal-agent-benchmark:september-2026":"29583bd7ab4390fc3584b502e8ceea55cd61b6dc5bd2e9f544f627c6a31d0a5c","version:healthbench:consensus":"cd203498989c75145370520d816f23f67f7a2c178bbe3e18ea44f873c9e93c79","version:healthbench:hard":"07fc98084080c01942b2b7defa46a82e3329307c173421c6c3e58f28007ae646","version:healthbench:healthbench":"1a2e889fa16087cfb08ec9d0c08875714e45d39680d58928c784f957a7215e55","version:hle-verified:full-1811-item-set":"12cc85842ecc5827e90fad7a9c02b347728543fdca4fac2672b9262ea820f5f4","version:humanitys-last-exam:full-set-no-tools":"30a6c9b7d63f2993014a2d857065416e4080a3102e378babfc84b4199750b9c4","version:humanitys-last-exam:full-set-scale-ai":"1a5c1ab28b58e8b21403fea961989a14c8bfb7075fb6fa708a6f854be2d21723","version:humanitys-last-exam:full-set-with-tools":"706826b8f163b920f2d9b4b4c1a55e4bc53ef09640919e83898b080ae4b4e925","version:humanitys-last-exam:no-tools-gpt-5-2":"f968aa4f7ca26574ac374372a6b46abeb8fd53c103b4c298df8cba7691336a0a","version:humanitys-last-exam:search-python-gpt-5-2":"34b6665d559072643bd943326d2a3a142ee26ed9d77bc1695e8d5a6559e4a01e","version:humanitys-last-exam:text-only-mercor":"8578f419b4371ab34d95ac515bdaf86ddd4de483b1d8150c912494e948baa74c","version:humanitys-last-exam:text-only-scale-ai":"fe30fd104e23c15c57fc12c3456fec065cd99f77a851997ed2da42567f1ec4ea","version:ifbench:original":"5e93448db484a219a67fcf4eea692f1c1b735075300ea575ed992726c5886599","version:ifeval:original":"5ec9151d4ce7314c817cbfcb35793cbb4bb33bf3db8fed9dfae149ad8c173a67","version:ipho:2025-theory":"b9fbfd365a820a9ae231c99b656ef39b9fe7b0871d9c0db15f849ee879e085a4","version:jobbench:main-65-tasks":"d619843fa247a4b67cd0264dae4e87f9fa328902b4b2d479871d03146dd50f8e","version:labbench2:terminal-internet-september-2026":"92c790aef7453813f813ba5fcf5dafae0316b6f6bcc652b086c791cb256e1d10","version:longbench:v2":"1834c0b80e0b7f4b190ba5aee63c2338826fa30daa74a6f35fe0d52cf7d60250","version:lvbench:1-fps-no-tools":"2e6ab529461fdce7f3a2e25bb1c86dba6d317bb1e3a8c0290d753ea44ecc0b4d","version:lvbench:1024-frames-agentic":"d71b18fb6f0e2f8428c0cdd1bedb89c0120fc43ffeb40e4d8ae6d43a063af734","version:lvbench:1024-frames-static":"5b98e5e37b809c2f5178336f8e5b339c49098829c0dd802909ea5fc93429f82d","version:math-vision:original":"f5be8b6564519ce89b543f91cefe866fff19fe4d31188738310f89e3e07a9a1b","version:math-vision:original-python-enabled":"d74f514738fe5394adfa4770a323b85231b23f740be91acbaedeff7b7e43659c","version:mathverse:mini":"9ccb33b7840d69d04cae026a518c7d8e029c4999bc40b6244b72638a91c8d101","version:mathvista:mini":"b73b67a2607b142a8ccd849d78ab6eed6e7232254e3eb4cde0c0069e0ccb800d","version:mcp-atlas:public-april-2026":"de37d2b83f353e893582e961e6c0e6fc8bc2eebac6fc3e2506820e34962799fa","version:medxpertqa:mm":"dae208e39332a4f1914b232d6f2bd565c539e8b5a9c8bd427e16034412b4126c","version:medxpertqa:mm-mercor":"17cf534f93036bc335bf01d4a512e36133c467dc14adf5f7ac0b7e4e3d81a84e","version:medxpertqa:text":"96500bcd23deed5c487e951bf573eefc675428a4e2a6037f5ae488da2e6e1443","version:milu:original":"d07edfc6d3eb8ed7bfcf24c925eec43455d26a11dc91664aba1eefdfdf2bfe45","version:mmlu-pro:original":"f5c53956b3401a0fd236c64b48f8c25259ad846035b4cbc4833e920f17e63b83","version:mmlu-pro:original-mercor":"d9314793e80dd505fa518d0ee31175f5b8d0f594c712153e49205fc6a94a453d","version:mmlu-pro:original-vals-ai":"871adea4f1358badaa254dd9f07414c1c167f69b5038c675447a47579369b9a5","version:mmlu:mmlu":"7aed05e060e646f74b41d79d6e5940b02e460dd96649ff986cba5fccf5bb0223","version:mmmlu:original":"7cb851b60d38a8df1c5728e2e91c6c710170f468e793d27cb9c2dc641744016b","version:mmmu-pro:1730-mercor":"6f6446ea84ad4d3203417ed0684b1888e93ac3f779c858997c3935c015db1f74","version:mmmu-pro:no-tools":"f5a64feec5f453b7e7d79254103ed9613f9f75f44d7991d4879cbf5311e574a2","version:mmmu-pro:vals-ai":"11584c582e8952d2f9ef8eb26bc95cb4151368c74b1a21738cfc95b96132d0c3","version:mmmu-pro:with-python":"472b35bf667af1347ff93ca9c1a25cac08df68c305b64291eff209bb703e7f48","version:mmmu-pro:with-tools":"cd77201a6facd4964de66d1ef7af9b636fea96ce34ddc32912a427673ac6e7da","version:mmmu:mmmu":"49111b5eb766e280f74a2f4ed3cb9ae716c4e18683415775b67593046214e9f8","version:mmstar:original":"68283c3111d35010cceeee86487273ab3da6a00978fd38420c400033232a55b3","version:mrcr:v2-8-needle-128k-256k-gpt-5-2":"9eabb4e04a762adebc65e8a23a489f984adb25b00877ac03d835574b7289bc75","version:mrcr:v2-8-needle-256k-512k-o200k-base":"307c558ff23265b7f38670773df2dac8837586a6120e0b141f1a87b24e772211","version:mrcr:v2-8-needle-512k-1m-o200k-base":"cd0b7ffae4d0ef52dcb63a3fe5d05b0afd8cbcaef0ea796764b88eb099f2af38","version:mtvqa:test":"2c11af8882ba371cb3e0cad0814311df4e43c0be634e6a786dbc4ef9ac553f63","version:multi-swe-bench:original":"3be0c6a9f26a111833da15ba72253769c2d7d704d6981216eada2a08cc26e0ac","version:nl2repo:original":"f2f2d556924ec1cae87168e1baa44946716a5c6a3cc774b35b8f473ebac22ebf","version:ocrbench:original":"a935b0a233bb5e617f72ba53a565b0cc0327400568653557e3b7d067906d9d7f","version:osworld:2.0-v2026.06.24-binary":"f0296e76fc99a2879443db4b4f6c5c3a8b20132ad83122d96047389f691e5117","version:osworld:2.0-v2026.06.24-partial":"4844c9afbf07f002bc278d675439356d4d00134bf07b2086610e96354285b425","version:osworld:2.0-v2026.08.08-binary":"c1d3c08deeffe686fd27aa84f0f24f858c6d99f695672aa37be3c46916917386","version:osworld:2.0-v2026.08.08-offline-partial":"b16c62ad7f171608cc2d7ca23075d0c2d32405b56571f7ad6c1cd112aa3b0192","version:osworld:2.0-v2026.08.08-offline-partial-max-3":"bd5596b2cc3042278f1b5e7f22fdea2dbecd0f0a2aae17720888c1d53686f741","version:osworld:2.0-v2026.08.08-partial":"90468b8061b049867ddbeb8ccfff6427296f454bb0a2f14c2937588f97d7d8f1","version:osworld:2.0-v2026.08.08-strict":"1eea709734c6cae52faadbff7773827dd15fd0f3bdce3d82b54cd16cc9b9dfba","version:osworld:verified":"52817ee8cad8807dd6ca8237c993115fe5ab5fc86eb3e5346720560d0fb1b2ea","version:osworld:verified-100-steps":"f4e159cd0e3f5f8bb41df670ed5faa12115ffd1cd50c8510ec4f74574aa88da4","version:osworld:verified-15-steps":"0957b89201dfdce28403e003b96e14e942935245fd3c663de636516d41a0f282","version:osworld:verified-50-steps":"6bc4ec9c5d09226532a1fe951eba981d7486eba05ad2848d9134080e73b70938","version:paperbench:code-dev":"72e1fd5f546c8f099f6ff4accfa20d001e7962eebe3219a4c2c75408d8cf330c","version:perceptionbench:original":"ce12bf055c36cfc4b395bdfb6060aa314d75c9fd67a552656afe1dc4bf98c01e","version:phage-plasmid-co-evolution:original":"cd85c52047dfcec05f01d493d2f8af03f86d024a63098cb3dd78ba9eda69e392","version:posttrainbench:1.1-claude-code":"a27b14e7e9d840372b7ee8f660882d6d243eabe522d6b83da32454de9c9e885e","version:posttrainbench:1.1-codex-cli":"0d71bfcedeb1bd6f76c382aec73e6348a7ab0ab9f378ab629399287cabffb4b4","version:posttrainbench:1.1-cursor-cli":"9d6accf3bff8d36c2a7dda644153227b98bcc62b4452cb895dc26cc7501f438e","version:posttrainbench:1.1-opencode":"bda32e615abfa032609b0db542eebc53c2cc612cb5531b3c4a3b5c9edaf90b35","version:posttrainbench:1.2-claude-code":"82ec75a3f450e5992c737d41b25fab10b3d3c4e3560e5f3ceaea675f1038a0d5","version:posttrainbench:1.2-codex-cli":"730a2231576fbd0eef83411a8e9336ce60b94f1dc26b247063af0bd5547bd2fc","version:posttrainbench:1.2-cursor-cli":"27002dde911bdd8ead402d53a1cd4073b52c96696b351851cf254cf6928d899a","version:posttrainbench:1.2-opencode":"0d3c850e14f4574a2535755b5daa0b93f37477472766638e245c8c11a137e638","version:realworldqa:original":"2363b8532ab689e8eb209120dcf93603c2930b9f347fe171073bcfcfd9daf683","version:riemann-bench:october-2026":"85d93aafd1e2a41a7841c565a2190f90f76a575748b7a1d80f7fe34b18d921a8","version:riemann-bench:september-2026-leaderboard":"1390aefd76529420e58ede39be320bfeaf77e3c95028ba99d829b985bafb933c","version:scicode:original":"97f9f271f507f2990486e3dda464b570a67dd5c90f2a95f43228707e1aec134c","version:screenspot-pro:no-tools":"0d669290fedebe931488d641f5e9edc69bd490b708c7cb99ffcf7b86fede8936","version:screenspot-pro:with-python":"2fad91e508819eff97022ca05113323d3d33c549d4ece980c4d80c9bf56c74b0","version:shp2-protein-function-prediction:original":"a3434b80b44f78cc8554dd62f97ddce2406e167e1ce0ae9367fc08765e52680a","version:simpleqa-verified:original":"cda6132cef4775a6f9f3b706bffec4b904c4526eac86efa786aa56d339d1f332","version:simpleqa-verified:original-epoch-ai":"9070d963838213d2f703f4d52be9adf4ad3e158adef2e132888f4eb6bf85db2c","version:skillsbench:78-task-self-contained-opencode":"66f54055aae02bd223f1e76b69e8b7fa0aa15e514f26714f234e4ef3077f9768","version:skillsbench:86-task-with-skills":"52626b2ab45f73be9a460b46bd2be74473155dfc4df651926d0d4eb66eb84e5e","version:spatialbench:verified":"e903197d8e5d9c4c9526b5880a42ec2412189fa7fe86522cc54b1d472aedf790","version:strongreject:original":"20faf4f6d51f46f9b5401b5fe6dee945a83f2030aa6d8b399314f67af912929f","version:swe-atlas:codebase-qna-mercor-mini-swe-agent":"2995ab2ccb780b6b7066d18a4deeadf79f7a4620b4bd69df50402099c391448d","version:swe-atlas:codebase-qna-public-claude-code":"4951ff4cab34b01b98f61899e9ae2930140eca202ca5d4202dad2854044bf975","version:swe-atlas:codebase-qna-public-codex":"a3c72f94c6ea854659d4ef31eb8d329a0a4c45a070fd4873d8608f62673f8f95","version:swe-atlas:codebase-qna-public-mini-swe-agent":"c813f7f7d3453b6fea5b572f255f3ad514fcaaa767af6742a1141ef732aba7fa","version:swe-atlas:refactoring-claude-code":"d7c827df71c2bc38dc32c8965637523aa96c673dcc03c237a4a35363c19d9cb2","version:swe-atlas:refactoring-codex":"e11bb20b41331a04044209243ae6b47fc05631ccef6b6b619d79f51acbe930f0","version:swe-atlas:refactoring-gemini-cli":"e7f2d6db1674fb0d0f8d595ee0e3831132fbc70977cd746f965b291b3ebea525","version:swe-atlas:refactoring-mini-swe-agent":"27fa0e0bb0fdcab2fc56212aefa71b76515150a5ff01e57c34f7fd910f92dbd7","version:swe-bench-pro:private-scale-ai-mini-swe-agent":"8dda21acafd3edc1319a0ece91e5068fcfd9bb23baa44281bcad0b35cf55c0b1","version:swe-bench-pro:private-scale-ai-swe-agent":"14eb33c2d0ebc945c3a62d6174fbd80889eda6825b4dfb53a39efc62ab7fb8d1","version:swe-bench-pro:public":"25d68bb65626e4c6bcfd8ed3aa2aa42a4424c7159b14f94e60624763b33740b8","version:swe-bench-pro:public-github-copilot":"3a706a811ca500e75352855ae39c8e359b8e54f8049a02fa55630044b94bcef4","version:swe-bench-pro:public-qwen-refined":"f65901b006ca53989cac56d53c196f5218c0b308d2e8040240fec83b326a33fe","version:swe-bench-pro:public-qwen3-6-refined":"7cd73eccb42720134f9a3888bb27be5c615113eb84778dce9aff281cd2955fea","version:swe-bench-pro:public-scale-ai-mini-swe-agent":"e3a730417c2b418cb7bb780c6956cd258d580c3fcf3e904ef22be28b5d22054d","version:swe-bench-pro:public-scale-ai-swe-agent":"864826650ad7b168951b60fa4013f5d6ee334434a3220f49af0ea5edae61962b","version:swe-bench:multilingual":"872b94ff20dc680faff78c11a5f14906de603e151f62fcca9cdaa058c23d4f9a","version:swe-bench:multilingual-cursor-standard-harness":"dd2253e4f178f322368d67b4380969e578f2e82c3ba627af8137215308b97e92","version:swe-bench:multilingual-cursor-strict-harness":"ff588108f7eb85a12d188f9e16e5c495a4765f4a17a6d935428b7f290b0040b2","version:swe-bench:multilingual-github-copilot":"55be74b04f830a7a928e2db2890b9d27bde3f4f29e42ed50716bc9ac4b4ee700","version:swe-bench:multilingual-mercor-mini-swe-agent":"7e9665d7b03bc7c0c9151bd70ba83c7e45d3c9e8438ff322d5eda25117d3eb22","version:swe-bench:multilingual-mini-swe-agent":"97013437425570da6e467d3e8cdce4fb29496ee69b0c9642a7a7afbf3d9034f7","version:swe-bench:verified":"a4fa15b6a652ee3e330fd9b14ec6b095ff6f26f190fa6efb64682bcea9c902c2","version:swe-bench:verified-bash-only":"bc3bd55655d19197220d24b5b58c2997e4bdefcf879286bea1e05230270145e3","version:swe-bench:verified-droid":"d4a9c4b7a0243fcf1a442b768c2d17c90b5b32d2685ac9f6d2294a28da0d0306","version:swe-bench:verified-epoch-ai":"09c3b76907d2e527f1e70a0411399dd30f3ea4a0d14d8d17a2cc37b8e3ae5ea4","version:swe-bench:verified-github-copilot":"9aa0ae52d2c554cced73896e0dccd03d4679be6f523a817e45b153ae2628b427","version:swe-bench:verified-mercor-mini-swe-agent":"db7f053e6ed56b04972668f315061bb9a07ebd676b86c66f26e9c2dd11786dcb","version:swe-bench:verified-mini-swe-agent":"5fda1eda45c86e6aca6808f9d8e95dbecb437a8579ff0b3fedff133127175b04","version:swe-bench:verified-muse-spark-corrected-tests":"d8b32fa5499995c839148550735ad44200386cba2e21f026daa9bb28bb66832e","version:swe-bench:verified-opencode":"a060c437fbea60dd2ec9d3ed983f815636e24a4add2e6a60489d11aeb19219ae","version:swe-bench:verified-vals-ai-mini-swe-agent":"f7ca1b4356be41554c1e28554790c24c64d85c332d66909e16cb7c3426ea1401","version:swe-fficiency:original":"01ab8a1b642bfbe48a1e81b97965430fde3e3df0e971e8d3e7356e90a3dae7ae","version:tau3-bench:banking-alltools-retrieval-v1-0-1":"8adb20cef6c461b506bc2e548bfab8fe4ba4f1090701960a2a15a6caec4132fe","version:tau3-bench:banking-qwen-embeddings-retrieval-v1-0-1":"e512f1e09a0c0b9ff72e023362c3f9e63a3522f4fb004e2c323cb678b740898f","version:tau3-bench:banking-terminal-retrieval-v1-0-1":"6ac9d9206fac0e901ed180ee1d72dc931712d2063e25b0e67c4b4aa1a737956f","version:tau3-bench:banking-text-emb-3-large-retrieval-v1-0-1":"1690ff48f45ec9069796a22559f6bfb954d1bbc5880236da86856c2136967f16","version:tau3-bench:tau3-airline":"50227d190534e651a6809ab7d85ba0029f449b613a37c296cd675c4b8ec6fd0f","version:tau3-bench:tau3-banking":"a000cf592efeb13bf9f07f6a594b20fa6769b5a4530a12fedd65ec4865328094","version:tau3-bench:tau3-retail":"5be6fa3c97533347b4dc28e8ae103ed7613ba4664e0561ce2be6de075a71b629","version:tau3-bench:tau3-telecom":"26ce843c7fc970ceaa8a9c334a2f77ea5125122458342e3a8622d7aaf4cba409","version:terminal-bench:2-0":"dcad8ceef84849215b791a6121c7c705bd7f374d1099c613b7d84126686c55d0","version:terminal-bench:2-0-github-copilot":"41e8d324839904b556324534333d10807e979d8528e087d1d072077388015d4f","version:terminal-bench:2-0-qwen3-6-terminus-2":"5f6ec98a17aa2651bece883fc67276a45d133e95e27fbfd63f2b2084499d64c3","version:terminal-bench:2-0-qwen3-7-terminus-2-5h":"6b4bb94c56b83a250af91ecd89746ea8e83e79d0c03d0b4cf1eeda5cd3fd982e","version:terminal-bench:2-0-terminus-2":"76baccc48a31c36fd13637f083bf904e9587f5c08adce1b0c1a94a0f2326f024","version:terminal-bench:2-1":"d3a12cd9cca29170ac5ad8a637c651b1ee8a4f89d1d93fa379bc1fe4d8feed71","version:terminal-bench:2-1-claude-code":"1c9d30679127b810d189020682791772c3fa97abcc2f0313d98592e511ca9afc","version:terminal-bench:2-1-mini-swe-agent":"14af0d221641102931895d2ff8ca86d915dd74a6b5a322ab1fbf3ee1096f84fb","version:terminal-bench:2-1-muse-code":"dbb9a2ee5e62c171c18a4a43c7b0963f6653f5fbb148186518916d4d9df8852d","version:terminal-bench:2-1-terminus-2":"1ab34beaa359d683bbd3ce5afaf4f8d04ee07d0c4aa601fc24d6646a49b13b4f","version:terminal-bench:2-1-thinking-machines-internal":"224a8e1bc7cc62a8c53f7e1ebc1c034bc055ab219696015be108e070eda8fe6f","version:terminal-bench:2.0-vals-ai-terminus-2":"1ee0e14515516ff9fcf14717afad74b62f243c229538eb4665f2ebebec9cb0b7","version:terminal-bench:2.1-mercor-terminus-2":"7935a9deae22914eb7df9de2e8d636e45c337600e623246aaf2642b16b703e37","version:terminal-bench:2.1-vals-ai-terminus-2":"ca70e1bf41828f51110c406bb01e94808a4eef04758e4767d72b1ef58ea3633f","version:terminal-bench:4.0":"8c774193b68752973f7fbcaec614b4b8003ee26d7e34e894a1cf499103be2798","version:terminal-bench:4.0-claude-code":"ab0d0f198144bfbb70c2eb371633bb3b66ad066846d7a379b356462d61a34fb6","version:terminal-bench:4.0-codex":"53bdb815036826ed5ad59f5d527ab7c60f4e31906696a07a840217a5438b8b4d","version:terminal-bench:4.0-grok-build":"4a6a7c9838df145cc7ad7b6f4d48b6e154015e8ee28c8f7d8c943c4b1f870c66","version:terminal-bench:4.0-mercor-mini-swe-agent":"28188f29079ed93b17a9b568a27132fc16a6337d40c6e8d42cc7c9667a34b59a","version:terminal-bench:4.0-mini-swe-agent":"804daf0bdf3381cf8191584d0cc1e023311dead1e3d6201a0fc26faa0d621225","version:terminal-bench:4.0-muse-code":"d00d633f915add285878d1bb064d8b683826b7ee33707f64c3774ffcf77503d9","version:terminal-bench:4.0-vals-ai-mini-swe-agent":"c83cdc5b004f2c73a381e3cf0d4787ba513b658371255bb785dadfd50a449a53","version:terminal-bench:science-0.1":"da499c37f41c72048b481c4f738b5be7fd94983bf7171b094e1a744569bc8ab3","version:terminal-bench:science-0.1-6x-verifier-timeout":"f4acb0655596d751df7de32324b276acec622d8d6debc3368545e241fd57071e","version:toolathlon:original":"9df532b6030bd33c555d0c59e15ed8374c3caba0c0f6a44d201b4a8f8575d0be","version:toolathlon:verified":"d5bc216b981d9582cd22fc052bf6968ce6542f5893714a08b0544065509a6246","version:vals-index:2.1":"ca80aa155925d2ed503750a7dee3b1cbd453bdaaf02e4d50883e3f7f4e0ae57e","version:vibe-code-bench:1.1-claude-code-october-2026":"25b0f3f7ed0747e1f60cad9710b1848f0beed752e7594c0fe4b44d2559194ffb","version:vibe-code-bench:1.1-codex-october-2026":"efaee3bc7129c274af8a0c9d9e6e0b37663607f97ef7271a30d0e2aaeb0583f3","version:vibe-code-bench:1.1-cursor-cli-october-2026":"9521ad5805d0b93701f63f1cf3db592a82c7dd1636aae06aa0503ed9ee8e613d","version:vibe-code-bench:1.1-factory-october-2026":"b42c3394a0938fede1921d3f84cd27d550b25a9ea6f567b54a9a35be455a2a06","version:vibe-code-bench:1.1-openhands-october-2026":"b73484665cfee40a6f6384d40ae6a5a96c6c99d82d091df1171e211ceca14ba6","version:vibe-code-bench:1.1-openhands-september-2026":"58d3647c3596ec5121b2ab2ae0a80b555fc0f5a8583e181825abaf9d281eaaf6","version:video-mme:original-with-subtitles":"712c399e11df2e83ee8ce826b65c0086b8b6b44be369dbec32ef251e894adbc7","inventory":"93e8a803b1d3cba91f3b3442733777adbdf389f3c97114f06b6b672dc3b8543b","featured":"d248b2105bc850f0d67d8fb1ab31b3e93668ab3bfcce8b0c193721493b9887c9","comparisons":"cfc780648991ce341f3aee9edaf3c06f34ddcb9133c31910293d88b53de89598"}}