SPB Git

Repository Public Research preview

eval-gpt-6-luna.run1.json 5.0 KB 219 lines json

1{2  "author": "gpt-6-luna",3  "date": "2026-11-10T05:58:38.486Z",4  "tasks": 16,5  "valid_without": 8,6  "valid_with": 15,7  "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: 'minimal' 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: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.",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": false,117        "status": 400,118        "message": "Invalid schema for response_format 'person': In context=(), 'required' is required to be supplied and to be an array including every key in properties. Missing 'email'.",119        "api": "responses"120      },121      "with": {122        "accepted": true,123        "api": "responses"124      }125    },126    {127      "task": "terra61-vision",128      "target": "gpt-6.1-terra",129      "without": {130        "accepted": false,131        "status": 400,132        "message": "Error while downloading file. Upstream status code: 400.",133        "api": "responses"134      },135      "with": {136        "accepted": false,137        "status": 400,138        "message": "Error while downloading file. Upstream status code: 400.",139        "api": "responses"140      }141    },142    {143      "task": "o3-search",144      "target": "o3",145      "without": {146        "accepted": false,147        "status": 400,148        "message": "Tool choices other than 'auto' are not supported with model 'o3' and the following tool types: 'web_search_preview'.",149        "api": "responses"150      },151      "with": {152        "accepted": true,153        "api": "responses"154      }155    },156    {157      "task": "gpt5mini-xhigh",158      "target": "gpt-5-mini",159      "without": {160        "accepted": true,161        "api": "responses"162      },163      "with": {164        "accepted": true,165        "api": "responses"166      }167    },168    {169      "task": "gpt54-creative",170      "target": "gpt-5.4",171      "without": {172        "accepted": false,173        "status": 400,174        "message": "Unsupported parameter: 'temperature' is not supported with this model.",175        "api": "responses"176      },177      "with": {178        "accepted": true,179        "api": "responses"180      }181    },182    {183      "task": "codex53-chat",184      "target": "gpt-5.3-codex",185      "without": {186        "accepted": true,187        "api": "responses"188      },189      "with": {190        "accepted": true,191        "api": "responses"192      }193    },194    {195      "task": "luna6-tool-result",196      "target": "gpt-6-luna",197      "without": {198        "accepted": true,199        "api": "responses"200      },201      "with": {202        "accepted": true,203        "api": "responses"204      }205    },206    {207      "task": "sol61-plain",208      "target": "gpt-6.1-sol",209      "without": {210        "accepted": true,211        "api": "responses"212      },213      "with": {214        "accepted": true,215        "api": "responses"216      }217    }218  ]219}
Files main
Menu

Theme