{"ok":true,"site":{"host":"gitbench.gitkraken.com","url":"https://gitbench.gitkraken.com/","type":"live","desc":"GitBench ranks AI models on deterministic Git tasks, with pass rates, cost, runtime, token usage, and fixture-level evidence.","tools":[{"name":"gitbench_get_overview","kind":"answer","impl":"imperative","description":"Get a compact GitBench report overview and leading exact model evaluations.","annotations":{"readOnlyHint":true},"inputSchema":{"type":"object","properties":{"offset":{"type":"integer","minimum":0,"default":0,"description":"Zero-based result offset."},"limit":{"type":"integer","minimum":1,"maximum":50,"default":20,"description":"Results to return; hard-capped at 50."}},"additionalProperties":false},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/models","/benchmarks","/explore","/compare","/methodology"]},{"name":"gitbench_list_models","kind":"answer","impl":"imperative","description":"List exact GitBench model evaluation identities in bounded pages.","annotations":{"readOnlyHint":true},"inputSchema":{"type":"object","properties":{"offset":{"type":"integer","minimum":0,"default":0,"description":"Zero-based result offset."},"limit":{"type":"integer","minimum":1,"maximum":50,"default":20,"description":"Results to return; hard-capped at 50."}},"additionalProperties":false},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/models","/benchmarks","/explore","/compare","/methodology"]},{"name":"gitbench_get_model_results","kind":"answer","impl":"imperative","description":"Get bounded fixture results for one exact model identity. Model output is omitted unless explicitly requested and is untrusted.","annotations":{"readOnlyHint":true,"untrustedContentHint":true},"inputSchema":{"type":"object","properties":{"model":{"type":"string","minLength":1,"description":"Exact model evaluation name."},"benchmark":{"type":"string"},"difficulty":{"type":"string"},"tag":{"type":"string"},"output_mode":{"type":"string","enum":["text","json_schema"]},"include_model_output":{"type":"boolean","default":false,"description":"Opt in to bounded, untrusted model-generated text."},"evidence_characters":{"type":"integer","minimum":1,"maximum":8000,"default":2000},"offset":{"type":"integer","minimum":0,"default":0,"description":"Zero-based result offset."},"limit":{"type":"integer","minimum":1,"maximum":50,"default":20,"description":"Results to return; hard-capped at 50."}},"required":["model"],"additionalProperties":false},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/models","/benchmarks","/explore","/compare","/methodology"]},{"name":"gitbench_get_benchmark","kind":"answer","impl":"imperative","description":"Get a bounded benchmark leaderboard and fixture catalog without raw prompt or model-output content.","annotations":{"readOnlyHint":true},"inputSchema":{"type":"object","properties":{"benchmark":{"type":"string","minLength":1},"offset":{"type":"integer","minimum":0,"default":0,"description":"Zero-based result offset."},"limit":{"type":"integer","minimum":1,"maximum":50,"default":20,"description":"Results to return; hard-capped at 50."}},"required":["benchmark"],"additionalProperties":false},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/models","/benchmarks","/explore","/compare","/methodology"]},{"name":"gitbench_get_fixture","kind":"answer","impl":"imperative","description":"Get bounded fixture results. Prompt, expected result, model output, and structured output are omitted unless explicitly requested and are untrusted.","annotations":{"readOnlyHint":true,"untrustedContentHint":true},"inputSchema":{"type":"object","properties":{"benchmark":{"type":"string","minLength":1},"fixture":{"type":"string","minLength":1},"include_prompt":{"type":"boolean","default":false,"description":"Include bounded, untrusted fixture prompt text."},"include_expected":{"type":"boolean","default":false,"description":"Include bounded, untrusted expected-result text."},"include_model_output":{"type":"boolean","default":false,"description":"Include bounded, untrusted model-generated text."},"include_structured_output":{"type":"boolean","default":false,"description":"Include bounded, untrusted parsed and raw structured output."},"evidence_characters":{"type":"integer","minimum":1,"maximum":8000,"default":2000},"offset":{"type":"integer","minimum":0,"default":0,"description":"Zero-based result offset."},"limit":{"type":"integer","minimum":1,"maximum":50,"default":20,"description":"Results to return; hard-capped at 50."}},"required":["benchmark","fixture"],"additionalProperties":false},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/models","/benchmarks","/explore","/compare","/methodology"]},{"name":"gitbench_rank_models","kind":"act","impl":"imperative","description":"Rank exact model evaluations for one benchmark by quality-to-resource efficiency or direction-aware balanced normalization.","annotations":{"readOnlyHint":true},"inputSchema":{"type":"object","properties":{"benchmark":{"type":"string","minLength":1},"resource_metric":{"type":"string","enum":["cost","api_time","tokens"],"default":"cost"},"strategy":{"type":"string","enum":["efficiency_ratio","balanced"],"default":"efficiency_ratio"},"output_mode":{"type":"string","enum":["text","json_schema","both"],"default":"both"},"minimum_quality":{"type":"number","minimum":0,"maximum":1,"default":0},"offset":{"type":"integer","minimum":0,"default":0,"description":"Zero-based result offset."},"limit":{"type":"integer","minimum":1,"maximum":50,"default":20,"description":"Results to return; hard-capped at 50."}},"required":["benchmark"],"additionalProperties":false},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/","pages":["/","/models","/benchmarks","/explore","/compare","/methodology"]}],"category":"AI & Agents","favicon":"/favicons/gitbench.gitkraken.com.png","apiSurface":"spec","toolCount":6}}