SPB Git

Repository Public Research preview

eval-gpt-6.1-terra.json 4.5 KB 211 lines json

1{2  "author": "gpt-6.1-terra",3  "date": "2026-11-10T05:59:14.954Z",4  "tasks": 16,5  "valid_without": 11,6  "valid_with": 16,7  "rows": [8    {9      "task": "sol61-deterministic",10      "target": "gpt-6.1-sol",11      "without": {12        "accepted": false,13        "status": 400,14        "message": "Unsupported parameter: 'temperature' is not supported with this model.",15        "api": "responses"16      },17      "with": {18        "accepted": true,19        "api": "responses"20      }21    },22    {23      "task": "luna6-low-temperature",24      "target": "gpt-6-luna",25      "without": {26        "accepted": false,27        "status": 400,28        "message": "Unsupported parameter: 'temperature' is not supported with this model.",29        "api": "responses"30      },31      "with": {32        "accepted": true,33        "api": "responses"34      }35    },36    {37      "task": "astra6-fast-cheap",38      "target": "gpt-6-astra",39      "without": {40        "accepted": false,41        "status": 400,42        "message": "Unsupported value: 'none' is not supported with the 'gpt-6-astra' model. Supported values are: 'low', 'medium', 'high', 'xhigh', and 'max'.",43        "api": "responses"44      },45      "with": {46        "accepted": true,47        "api": "responses"48      }49    },50    {51      "task": "gpt5-no-reasoning",52      "target": "gpt-5",53      "without": {54        "accepted": true,55        "api": "responses"56      },57      "with": {58        "accepted": true,59        "api": "responses"60      }61    },62    {63      "task": "gpt55pro-chat",64      "target": "gpt-5.5-pro",65      "without": {66        "accepted": true,67        "api": "responses"68      },69      "with": {70        "accepted": true,71        "api": "responses"72      }73    },74    {75      "task": "sol61-chat-tools",76      "target": "gpt-6.1-sol",77      "without": {78        "accepted": true,79        "api": "responses"80      },81      "with": {82        "accepted": true,83        "api": "responses"84      }85    },86    {87      "task": "luna6-short-answer",88      "target": "gpt-6-luna",89      "without": {90        "accepted": false,91        "status": 400,92        "message": "Unsupported parameter: 'stop' is not supported with this model.",93        "api": "chat"94      },95      "with": {96        "accepted": true,97        "api": "chat"98      }99    },100    {101      "task": "gpt41-effort",102      "target": "gpt-4.1",103      "without": {104        "accepted": true,105        "api": "responses"106      },107      "with": {108        "accepted": true,109        "api": "responses"110      }111    },112    {113      "task": "sol61-json",114      "target": "gpt-6.1-sol",115      "without": {116        "accepted": true,117        "api": "responses"118      },119      "with": {120        "accepted": true,121        "api": "responses"122      }123    },124    {125      "task": "terra61-vision",126      "target": "gpt-6.1-terra",127      "without": {128        "accepted": true,129        "api": "responses"130      },131      "with": {132        "accepted": true,133        "api": "responses"134      }135    },136    {137      "task": "o3-search",138      "target": "o3",139      "without": {140        "accepted": false,141        "status": 400,142        "message": "Tool choices other than 'auto' are not supported with model 'o3' and the following tool types: 'web_search_preview'.",143        "api": "responses"144      },145      "with": {146        "accepted": true,147        "api": "responses"148      }149    },150    {151      "task": "gpt5mini-xhigh",152      "target": "gpt-5-mini",153      "without": {154        "accepted": true,155        "api": "responses"156      },157      "with": {158        "accepted": true,159        "api": "responses"160      }161    },162    {163      "task": "gpt54-creative",164      "target": "gpt-5.4",165      "without": {166        "accepted": true,167        "api": "responses"168      },169      "with": {170        "accepted": true,171        "api": "responses"172      }173    },174    {175      "task": "codex53-chat",176      "target": "gpt-5.3-codex",177      "without": {178        "accepted": true,179        "api": "responses"180      },181      "with": {182        "accepted": true,183        "api": "responses"184      }185    },186    {187      "task": "luna6-tool-result",188      "target": "gpt-6-luna",189      "without": {190        "accepted": true,191        "api": "responses"192      },193      "with": {194        "accepted": true,195        "api": "responses"196      }197    },198    {199      "task": "sol61-plain",200      "target": "gpt-6.1-sol",201      "without": {202        "accepted": true,203        "api": "responses"204      },205      "with": {206        "accepted": true,207        "api": "responses"208      }209    }210  ]211}
Files main
Menu

Theme