SPB Git

Repository Public Research preview

eval-gpt-6-luna.json 4.6 KB 213 lines json

1{2  "author": "gpt-6-luna",3  "date": "2026-11-10T05:59:01.861Z",4  "tasks": 16,5  "valid_without": 10,6  "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": "Invalid 'max_output_tokens': integer below minimum value. Expected a value >= 16, but got 5 instead.",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": 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": false,167        "status": 400,168        "message": "Unsupported parameter: 'temperature' is not supported with this model.",169        "api": "responses"170      },171      "with": {172        "accepted": true,173        "api": "responses"174      }175    },176    {177      "task": "codex53-chat",178      "target": "gpt-5.3-codex",179      "without": {180        "accepted": true,181        "api": "responses"182      },183      "with": {184        "accepted": true,185        "api": "responses"186      }187    },188    {189      "task": "luna6-tool-result",190      "target": "gpt-6-luna",191      "without": {192        "accepted": true,193        "api": "responses"194      },195      "with": {196        "accepted": true,197        "api": "responses"198      }199    },200    {201      "task": "sol61-plain",202      "target": "gpt-6.1-sol",203      "without": {204        "accepted": true,205        "api": "responses"206      },207      "with": {208        "accepted": true,209        "api": "responses"210      }211    }212  ]213}
Files main
Menu

Theme