SPB Git

Repository Public Research preview

eval-claude-opus-5-5.json 4.3 KB 187 lines json

1{2  "author": "claude-opus-5-5",3  "date": "2026-11-10T05:22:40.534Z",4  "tasks": 16,5  "accepted_without": 8,6  "accepted_with": 16,7  "rows": [8    {9      "task": "opus55-deterministic",10      "target": "claude-opus-5-5",11      "without": {12        "accepted": false,13        "status": 400,14        "message": "temperature: Extra inputs are not permitted"15      },16      "with": {17        "accepted": true18      }19    },20    {21      "task": "opus55-deep-thinking",22      "target": "claude-opus-5-5",23      "without": {24        "accepted": false,25        "status": 400,26        "message": "\"thinking.type.enabled\" is not supported for this model. Use \"thinking.type.adaptive\" and \"output_config.effort\" to control thinking behavior."27      },28      "with": {29        "accepted": true30      }31    },32    {33      "task": "sonnet55-force-tool",34      "target": "claude-sonnet-5-5",35      "without": {36        "accepted": false,37        "status": 400,38        "message": "tool_choice: type \"tool\" and \"any\" are not supported for this model."39      },40      "with": {41        "accepted": true42      }43    },44    {45      "task": "fable52-no-thinking",46      "target": "claude-fable-5-2",47      "without": {48        "accepted": false,49        "status": 400,50        "message": "\"thinking.type.disabled\" is not supported for this model. Use \"thinking.type.adaptive\" and \"output_config.effort\" to control thinking behavior."51      },52      "with": {53        "accepted": true54      }55    },56    {57      "task": "sonnet55-no-thinking",58      "target": "claude-sonnet-5-5",59      "without": {60        "accepted": false,61        "status": 400,62        "message": "To turn thinking off on this model, send \"thinking\": {\"type\": \"between_tools\"} instead of {\"type\": \"disabled\"}. The model does not think before responding. The "63      },64      "with": {65        "accepted": true66      }67    },68    {69      "task": "opus55-json",70      "target": "claude-opus-5-5",71      "without": {72        "accepted": true73      },74      "with": {75        "accepted": true76      }77    },78    {79      "task": "haiku45-thinking",80      "target": "claude-haiku-4-5-20251001",81      "without": {82        "accepted": true83      },84      "with": {85        "accepted": true86      }87    },88    {89      "task": "opus46-max-effort",90      "target": "claude-opus-4-6",91      "without": {92        "accepted": true93      },94      "with": {95        "accepted": true96      }97    },98    {99      "task": "sonnet45-effort",100      "target": "claude-sonnet-4-5-20250929",101      "without": {102        "accepted": true103      },104      "with": {105        "accepted": true106      }107    },108    {109      "task": "haiku55-creative",110      "target": "claude-haiku-5-5",111      "without": {112        "accepted": false,113        "status": 400,114        "message": "temperature: Extra inputs are not permitted"115      },116      "with": {117        "accepted": true118      }119    },120    {121      "task": "opus55-long-output",122      "target": "claude-opus-5-5",123      "without": {124        "accepted": true125      },126      "with": {127        "accepted": true128      }129    },130    {131      "task": "opus5-fast",132      "target": "claude-opus-5",133      "without": {134        "accepted": false,135        "status": 400,136        "message": "To use the `speed` parameter with 'claude-opus-5', send the `anthropic-beta: fast-mode-2026-02-01` header."137      },138      "with": {139        "accepted": true,140        "no_access": true,141        "status": 429142      }143    },144    {145      "task": "sonnet5-system-mid",146      "target": "claude-sonnet-5",147      "without": {148        "accepted": true149      },150      "with": {151        "accepted": true152      }153    },154    {155      "task": "opus47-plain",156      "target": "claude-opus-4-7",157      "without": {158        "accepted": true159      },160      "with": {161        "accepted": true162      }163    },164    {165      "task": "fable51-tool-json",166      "target": "claude-fable-5-1",167      "without": {168        "accepted": false,169        "status": 400,170        "message": "tool_choice: type \"tool\" and \"any\" are not supported for this model."171      },172      "with": {173        "accepted": true174      }175    },176    {177      "task": "haiku55-plain",178      "target": "claude-haiku-5-5",179      "without": {180        "accepted": true181      },182      "with": {183        "accepted": true184      }185    }186  ]187}
Files main
Menu

Theme