# Benchmarks

## Get Benchmark models.

> Get all Benchmark models. If \`benchmarkTypeId\` is provided, it will return the scores calculated for that specific benchmark type. If not provided, it will return the total score aggregated across all benchmark types.

```json
{"openapi":"3.0.4","info":{"title":"API","version":"v1.0"},"tags":[{"name":"BenchmarkV","description":"The API provides endpoints for fetching data related to Benchmark and details about categories, types, models and probe runs."}],"servers":[{"url":"https://api.probe.splx.ai","description":"EU Server"},{"url":"https://us.api.probe.splx.ai","description":"US Server"}],"security":[{"API Key":[]}],"components":{"securitySchemes":{"API Key":{"type":"apiKey","description":"API Key for authentication","name":"X-Api-Key","in":"header"}},"schemas":{"BenchmarkModelDto":{"required":["id","name","provider"],"type":"object","properties":{"id":{"type":"integer","description":"Unique identifier for the Benchmark model.","format":"int32"},"name":{"type":"string","description":"Name of the Benchmark model.","nullable":true},"provider":{"type":"string","description":"Provider or organization that created/maintains the model.","nullable":true},"benchmarkDate":{"type":"string","description":"Date when the Benchmark was executed or last updated.","format":"date-time","nullable":true},"url":{"type":"string","description":"Optional URL providing additional information or documentation about the model.","nullable":true},"scores":{"type":"object","additionalProperties":{"type":"number","format":"float"},"description":"Performance scores organized by category name. Values represent Benchmark results.","nullable":true}},"additionalProperties":false,"description":"Benchmark model information including identification, provider details, and performance scores."},"BenchmarkModelWithDetailsDto":{"allOf":[{"$ref":"#/components/schemas/BenchmarkModelDto"},{"required":["failedCount","passedCount","totalCount"],"type":"object","properties":{"description":{"type":"string","description":"Optional description providing detailed information about the Benchmark model.","nullable":true},"config":{"type":"object","additionalProperties":{},"description":"Configuration settings used for the Benchmark model execution.","nullable":true},"metadata":{"type":"object","additionalProperties":{},"description":"Additional metadata associated with the Benchmark model.","nullable":true},"totalCount":{"type":"integer","description":"Total number of test cases executed during the Benchmark run.","format":"int32"},"passedCount":{"type":"integer","description":"Number of test cases that passed during the Benchmark execution.","format":"int32"},"failedCount":{"type":"integer","description":"Number of test cases that failed during the Benchmark execution.","format":"int32"},"ranks":{"type":"object","additionalProperties":{"type":"integer","format":"int32"},"description":"Ranking positions of the model across different Benchmark categories.","nullable":true}}}],"additionalProperties":false,"description":"Extended Benchmark model information including detailed configuration, execution statistics, and ranking data."},"ErrorResponse":{"required":["error"],"type":"object","properties":{"error":{"oneOf":[{"$ref":"#/components/schemas/ErrorDetailsDto"},{"$ref":"#/components/schemas/BadRequestErrorDetailsDto"}],"description":"Error object."}},"additionalProperties":false,"description":"Response payload for error."},"ErrorDetailsDto":{"required":["message"],"type":"object","properties":{"message":{"type":"string","description":"Error detailed message."},"code":{"type":"string","description":"Error code."}},"additionalProperties":false},"BadRequestErrorDetailsDto":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorDetailsDto"}],"properties":{"validationErrors":{"type":"object","additionalProperties":{"type":"array","items":{"type":"string"}},"description":"Specific validation errors.","nullable":true}},"additionalProperties":false},"UnauthorizedError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Unauthorized access error."},"UnauthorizedWithLogoutError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Unauthorized access error."},"ForbiddenError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Forbidden access error."},"InternalServerError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Internal Server error."},"NotFoundExampleError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Not Found error."}}},"paths":{"/api/v2/benchmarks/models":{"get":{"tags":["BenchmarkV"],"summary":"Get Benchmark models.","description":"Get all Benchmark models. If `benchmarkTypeId` is provided, it will return the scores calculated for that specific benchmark type. If not provided, it will return the total score aggregated across all benchmark types.","parameters":[{"name":"benchmarkTypeId","in":"query","schema":{"type":"integer","format":"int32"}}],"responses":{"200":{"description":"OK","content":{"application/json":{"schema":{"type":"array","items":{"oneOf":[{"$ref":"#/components/schemas/BenchmarkModelDto"},{"$ref":"#/components/schemas/BenchmarkModelWithDetailsDto"}],"description":"Benchmark model information including identification, provider details, and performance scores."}}}}},"400":{"description":"Bad Request","content":{"application/json":{"schema":{"oneOf":[{"$ref":"#/components/schemas/ErrorResponse"},{"$ref":"#/components/schemas/UnauthorizedError"},{"$ref":"#/components/schemas/UnauthorizedWithLogoutError"},{"$ref":"#/components/schemas/ForbiddenError"},{"$ref":"#/components/schemas/InternalServerError"},{"$ref":"#/components/schemas/NotFoundExampleError"}],"description":"Response payload for error."}}}},"401":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/UnauthorizedError"}}}},"403":{"description":"Forbidden","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ForbiddenError"}}}},"500":{"description":"Internal Server Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/InternalServerError"}}}}}}}}}
```

## Get Benchmark model details.

> Get details of a specific Benchmark model. If \`benchmarkTypeId\` is provided, it will return the scores calculated for that specific benchmark type. If not provided, it will return the total score aggregated across all benchmark types.

```json
{"openapi":"3.0.4","info":{"title":"API","version":"v1.0"},"tags":[{"name":"BenchmarkV","description":"The API provides endpoints for fetching data related to Benchmark and details about categories, types, models and probe runs."}],"servers":[{"url":"https://api.probe.splx.ai","description":"EU Server"},{"url":"https://us.api.probe.splx.ai","description":"US Server"}],"security":[{"API Key":[]}],"components":{"securitySchemes":{"API Key":{"type":"apiKey","description":"API Key for authentication","name":"X-Api-Key","in":"header"}},"schemas":{"BenchmarkModelWithDetailsDto":{"allOf":[{"$ref":"#/components/schemas/BenchmarkModelDto"},{"required":["failedCount","passedCount","totalCount"],"type":"object","properties":{"description":{"type":"string","description":"Optional description providing detailed information about the Benchmark model.","nullable":true},"config":{"type":"object","additionalProperties":{},"description":"Configuration settings used for the Benchmark model execution.","nullable":true},"metadata":{"type":"object","additionalProperties":{},"description":"Additional metadata associated with the Benchmark model.","nullable":true},"totalCount":{"type":"integer","description":"Total number of test cases executed during the Benchmark run.","format":"int32"},"passedCount":{"type":"integer","description":"Number of test cases that passed during the Benchmark execution.","format":"int32"},"failedCount":{"type":"integer","description":"Number of test cases that failed during the Benchmark execution.","format":"int32"},"ranks":{"type":"object","additionalProperties":{"type":"integer","format":"int32"},"description":"Ranking positions of the model across different Benchmark categories.","nullable":true}}}],"additionalProperties":false,"description":"Extended Benchmark model information including detailed configuration, execution statistics, and ranking data."},"BenchmarkModelDto":{"required":["id","name","provider"],"type":"object","properties":{"id":{"type":"integer","description":"Unique identifier for the Benchmark model.","format":"int32"},"name":{"type":"string","description":"Name of the Benchmark model.","nullable":true},"provider":{"type":"string","description":"Provider or organization that created/maintains the model.","nullable":true},"benchmarkDate":{"type":"string","description":"Date when the Benchmark was executed or last updated.","format":"date-time","nullable":true},"url":{"type":"string","description":"Optional URL providing additional information or documentation about the model.","nullable":true},"scores":{"type":"object","additionalProperties":{"type":"number","format":"float"},"description":"Performance scores organized by category name. Values represent Benchmark results.","nullable":true}},"additionalProperties":false,"description":"Benchmark model information including identification, provider details, and performance scores."},"ErrorResponse":{"required":["error"],"type":"object","properties":{"error":{"oneOf":[{"$ref":"#/components/schemas/ErrorDetailsDto"},{"$ref":"#/components/schemas/BadRequestErrorDetailsDto"}],"description":"Error object."}},"additionalProperties":false,"description":"Response payload for error."},"ErrorDetailsDto":{"required":["message"],"type":"object","properties":{"message":{"type":"string","description":"Error detailed message."},"code":{"type":"string","description":"Error code."}},"additionalProperties":false},"BadRequestErrorDetailsDto":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorDetailsDto"}],"properties":{"validationErrors":{"type":"object","additionalProperties":{"type":"array","items":{"type":"string"}},"description":"Specific validation errors.","nullable":true}},"additionalProperties":false},"UnauthorizedError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Unauthorized access error."},"UnauthorizedWithLogoutError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Unauthorized access error."},"ForbiddenError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Forbidden access error."},"InternalServerError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Internal Server error."},"NotFoundExampleError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Not Found error."}}},"paths":{"/api/v2/benchmarks/models/{modelId}":{"get":{"tags":["BenchmarkV"],"summary":"Get Benchmark model details.","description":"Get details of a specific Benchmark model. If `benchmarkTypeId` is provided, it will return the scores calculated for that specific benchmark type. If not provided, it will return the total score aggregated across all benchmark types.","parameters":[{"name":"modelId","in":"path","required":true,"schema":{"type":"integer","format":"int64"}},{"name":"benchmarkTypeId","in":"query","schema":{"type":"integer","format":"int32"}}],"responses":{"200":{"description":"OK","content":{"application/json":{"schema":{"$ref":"#/components/schemas/BenchmarkModelWithDetailsDto"}}}},"400":{"description":"Bad Request","content":{"application/json":{"schema":{"oneOf":[{"$ref":"#/components/schemas/ErrorResponse"},{"$ref":"#/components/schemas/UnauthorizedError"},{"$ref":"#/components/schemas/UnauthorizedWithLogoutError"},{"$ref":"#/components/schemas/ForbiddenError"},{"$ref":"#/components/schemas/InternalServerError"},{"$ref":"#/components/schemas/NotFoundExampleError"}],"description":"Response payload for error."}}}},"401":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/UnauthorizedError"}}}},"403":{"description":"Forbidden","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ForbiddenError"}}}},"500":{"description":"Internal Server Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/InternalServerError"}}}}}}}}}
```

## Get Benchmark model probe runs.

> Get all probe runs for a specific benchmark model.

```json
{"openapi":"3.0.4","info":{"title":"API","version":"v1.0"},"tags":[{"name":"BenchmarkV","description":"The API provides endpoints for fetching data related to Benchmark and details about categories, types, models and probe runs."}],"servers":[{"url":"https://api.probe.splx.ai","description":"EU Server"},{"url":"https://us.api.probe.splx.ai","description":"US Server"}],"security":[{"API Key":[]}],"components":{"securitySchemes":{"API Key":{"type":"apiKey","description":"API Key for authentication","name":"X-Api-Key","in":"header"}},"schemas":{"BenchmarkProbeRunDto":{"required":["createdAt","failedCount","id","passedCount","probeCategoryId","probeCategoryName","probeId","probeName","score","totalCount"],"type":"object","properties":{"id":{"type":"integer","description":"Unique identifier for the Benchmark probe run.","format":"int32"},"passedCount":{"type":"integer","description":"Number of test cases that passed during the probe run.","format":"int32"},"failedCount":{"type":"integer","description":"Number of test cases that failed during the probe run.","format":"int32"},"totalCount":{"type":"integer","description":"Total number of test cases executed during the probe run.","format":"int32"},"score":{"type":"number","description":"Performance score calculated from the probe run results.","format":"float"},"probeId":{"type":"integer","description":"Unique identifier of the probe that was executed.","format":"int32"},"probeName":{"type":"string","description":"Name of the probe that was executed.","nullable":true},"probeCategoryId":{"type":"integer","description":"Unique identifier of the probe's category.","format":"int32"},"probeCategoryName":{"type":"string","description":"Name of the probe's category.","nullable":true},"createdAt":{"type":"string","description":"Timestamp when the probe run was created and executed.","format":"date-time"}},"additionalProperties":false,"description":"Benchmark probe run information including execution statistics, performance score, and probe identification."},"BenchmarkProbeRunWithResultsDto":{"allOf":[{"$ref":"#/components/schemas/BenchmarkProbeRunDto"},{"required":["results"],"type":"object","properties":{"results":{"type":"array","items":{"oneOf":[{"$ref":"#/components/schemas/BenchmarkProbeRunResultDto"},{"$ref":"#/components/schemas/BenchmarkProbeRunResultWithDetailsDto"}],"description":"Individual Benchmark probe run result containing attack details, execution strategy, and outcome status."},"description":"List of individual test case results from the probe run execution.","nullable":true}}}],"additionalProperties":false,"description":"Extended Benchmark probe run information including detailed individual test case results."},"BenchmarkProbeRunResultDto":{"required":["attackId","createdAt","id","redTeamer","status","strategy","variation"],"type":"object","properties":{"id":{"type":"integer","description":"Unique identifier for the probe run result.","format":"int32"},"attackId":{"type":"string","description":"Unique identifier for the attack scenario used in this test case.","nullable":true},"strategy":{"type":"string","description":"Strategy or methodology used for executing the test case.","nullable":true},"redTeamer":{"type":"string","description":"Red teamer or testing component responsible for executing this test case.","nullable":true},"variation":{"type":"string","description":"Variation or specific configuration of the test case.","nullable":true},"status":{"type":"string","description":"Execution status indicating the outcome of the test case (e.g., 'passed', 'failed', 'error').","nullable":true},"redTeamerLabels":{"type":"object","additionalProperties":{"type":"string"},"description":"Optional labels or metadata provided by the red teamer for additional context.","nullable":true},"createdAt":{"type":"string","description":"Timestamp when the probe run result was created.","format":"date-time"}},"additionalProperties":false,"description":"Individual Benchmark probe run result containing attack details, execution strategy, and outcome status."},"BenchmarkProbeRunResultWithDetailsDto":{"allOf":[{"$ref":"#/components/schemas/BenchmarkProbeRunResultDto"},{"required":["conversation","explanation"],"type":"object","properties":{"conversation":{"type":"array","items":{"type":"array","items":{"$ref":"#/components/schemas/MessageV2Dto"}},"description":"Complete conversation transcript showing the interaction flow during the test case execution.","nullable":true},"explanation":{"type":"string","description":"Detailed explanation or analysis of the test case result and its implications.","nullable":true}}}],"additionalProperties":false,"description":"Comprehensive Benchmark probe run result including detailed conversation logs and explanatory analysis."},"MessageV2Dto":{"required":["messageContents","role"],"type":"object","properties":{"role":{"type":"string","nullable":true},"messageContents":{"type":"array","items":{"$ref":"#/components/schemas/ContentDto"},"nullable":true}},"additionalProperties":false},"ContentDto":{"required":["contentType"],"type":"object","properties":{"text":{"type":"string","nullable":true},"encodedText":{"type":"string","nullable":true},"imageUrl":{"type":"string","nullable":true},"encodedImageUrl":{"type":"string","nullable":true},"contentType":{"type":"string","nullable":true},"audioUrl":{"type":"string","nullable":true},"encodedAudioUrl":{"type":"string","nullable":true},"documentUrl":{"type":"string","nullable":true},"encodedDocumentUrl":{"type":"string","nullable":true}},"additionalProperties":false},"ReportBenchmarkProbeRunWithResultsDto":{"allOf":[{"$ref":"#/components/schemas/BenchmarkProbeRunDto"},{"required":["attackStrategies","heatmaps","redTeamer","results","testCaseResults","variation"],"type":"object","properties":{"results":{"type":"array","items":{"oneOf":[{"$ref":"#/components/schemas/BenchmarkProbeRunResultDto"},{"$ref":"#/components/schemas/BenchmarkProbeRunResultWithDetailsDto"}],"description":"Individual Benchmark probe run result containing attack details, execution strategy, and outcome status."},"nullable":true},"attackStrategies":{"type":"string","nullable":true},"redTeamer":{"type":"string","nullable":true},"variation":{"type":"string","nullable":true},"heatmaps":{"nullable":true},"testCaseResults":{"type":"array","items":{"$ref":"#/components/schemas/ReportTestCaseResultSample"},"nullable":true}}}],"additionalProperties":false,"description":"Benchmark probe run information including execution statistics, performance score, and probe identification."},"ReportTestCaseResultSample":{"required":["attackId","isIncludedInReport","redTeamer","status","strategy","variation"],"type":"object","properties":{"id":{"type":"integer","format":"int32"},"attackId":{"type":"string","nullable":true},"attempt":{"type":"integer","format":"int32"},"variation":{"type":"string","nullable":true},"strategy":{"type":"string","nullable":true},"redTeamer":{"type":"string","nullable":true},"status":{"type":"string","nullable":true},"isIncludedInReport":{"type":"boolean"},"metadata":{"$ref":"#/components/schemas/ReportMetadataDto"}},"additionalProperties":false},"ReportMetadataDto":{"required":["baseUrl","targetId","workspaceId"],"type":"object","properties":{"baseUrl":{"type":"string","nullable":true},"workspaceId":{"type":"integer","format":"int32"},"targetId":{"type":"integer","format":"int32"},"testRunId":{"type":"integer","format":"int32","nullable":true},"probeRunId":{"type":"integer","format":"int32","nullable":true},"testCaseResultId":{"type":"integer","format":"int32","nullable":true}},"additionalProperties":false},"ErrorResponse":{"required":["error"],"type":"object","properties":{"error":{"oneOf":[{"$ref":"#/components/schemas/ErrorDetailsDto"},{"$ref":"#/components/schemas/BadRequestErrorDetailsDto"}],"description":"Error object."}},"additionalProperties":false,"description":"Response payload for error."},"ErrorDetailsDto":{"required":["message"],"type":"object","properties":{"message":{"type":"string","description":"Error detailed message."},"code":{"type":"string","description":"Error code."}},"additionalProperties":false},"BadRequestErrorDetailsDto":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorDetailsDto"}],"properties":{"validationErrors":{"type":"object","additionalProperties":{"type":"array","items":{"type":"string"}},"description":"Specific validation errors.","nullable":true}},"additionalProperties":false},"UnauthorizedError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Unauthorized access error."},"UnauthorizedWithLogoutError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Unauthorized access error."},"ForbiddenError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Forbidden access error."},"InternalServerError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Internal Server error."},"NotFoundExampleError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Not Found error."}}},"paths":{"/api/v2/benchmarks/models/{modelId}/runs":{"get":{"tags":["BenchmarkV"],"summary":"Get Benchmark model probe runs.","description":"Get all probe runs for a specific benchmark model.","parameters":[{"name":"modelId","in":"path","required":true,"schema":{"type":"integer","format":"int64"}},{"name":"benchmarkTypeId","in":"query","required":true,"schema":{"type":"integer","format":"int32"}}],"responses":{"200":{"description":"OK","content":{"application/json":{"schema":{"type":"array","items":{"oneOf":[{"$ref":"#/components/schemas/BenchmarkProbeRunDto"},{"$ref":"#/components/schemas/BenchmarkProbeRunWithResultsDto"},{"$ref":"#/components/schemas/ReportBenchmarkProbeRunWithResultsDto"}],"description":"Benchmark probe run information including execution statistics, performance score, and probe identification."}}}}},"400":{"description":"Bad Request","content":{"application/json":{"schema":{"oneOf":[{"$ref":"#/components/schemas/ErrorResponse"},{"$ref":"#/components/schemas/UnauthorizedError"},{"$ref":"#/components/schemas/UnauthorizedWithLogoutError"},{"$ref":"#/components/schemas/ForbiddenError"},{"$ref":"#/components/schemas/InternalServerError"},{"$ref":"#/components/schemas/NotFoundExampleError"}],"description":"Response payload for error."}}}},"401":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/UnauthorizedError"}}}},"403":{"description":"Forbidden","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ForbiddenError"}}}},"500":{"description":"Internal Server Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/InternalServerError"}}}}}}}}}
```

## Get details of a specific Benchmark probe run.

> Retrieve detailed information about a specific Benchmark probe run by its unique identifier, including results, execution metadata and conversation.

```json
{"openapi":"3.0.4","info":{"title":"API","version":"v1.0"},"tags":[{"name":"BenchmarkV","description":"The API provides endpoints for fetching data related to Benchmark and details about categories, types, models and probe runs."}],"servers":[{"url":"https://api.probe.splx.ai","description":"EU Server"},{"url":"https://us.api.probe.splx.ai","description":"US Server"}],"security":[{"API Key":[]}],"components":{"securitySchemes":{"API Key":{"type":"apiKey","description":"API Key for authentication","name":"X-Api-Key","in":"header"}},"schemas":{"BenchmarkV2ProbeRunWithResultsDto":{"allOf":[{"$ref":"#/components/schemas/BenchmarkV2ProbeRunDto"},{"required":["results"],"type":"object","properties":{"results":{"type":"array","items":{"$ref":"#/components/schemas/BenchmarkV2ProbeRunResultDto"},"description":"List of individual test case results from the probe run execution.","nullable":true}}}],"additionalProperties":false,"description":"Extended Benchmark probe run information including detailed individual test case results."},"BenchmarkV2ProbeRunDto":{"required":["createdAt","failedCount","id","passedCount","probeCategoryId","probeCategoryName","probeId","probeName","score","totalCount"],"type":"object","properties":{"id":{"type":"integer","description":"Unique identifier for the Benchmark probe run.","format":"int32"},"passedCount":{"type":"integer","description":"Number of test cases that passed during the probe run.","format":"int32"},"failedCount":{"type":"integer","description":"Number of test cases that failed during the probe run.","format":"int32"},"totalCount":{"type":"integer","description":"Total number of test cases executed during the probe run.","format":"int32"},"score":{"type":"number","description":"Performance score calculated from the probe run results.","format":"float"},"probeId":{"type":"integer","description":"Unique identifier of the probe that was executed.","format":"int32"},"probeName":{"type":"string","description":"Name of the probe that was executed.","nullable":true},"probeCategoryId":{"type":"integer","description":"Unique identifier of the probe's category.","format":"int32"},"probeCategoryName":{"type":"string","description":"Name of the probe's category.","nullable":true},"createdAt":{"type":"string","description":"Timestamp when the probe run was created and executed.","format":"date-time"}},"additionalProperties":false,"description":"Benchmark probe run information including execution statistics, performance score, and probe identification."},"BenchmarkV2ProbeRunResultDto":{"required":["attackId","conversation","createdAt","explanation","id","redTeamer","status","strategy","variation"],"type":"object","properties":{"id":{"type":"integer","description":"Unique identifier for the probe run result.","format":"int32"},"attackId":{"type":"string","description":"Unique identifier for the attack scenario used in this test case.","nullable":true},"strategy":{"type":"string","description":"Strategy or methodology used for executing the test case.","nullable":true},"redTeamer":{"type":"string","description":"Red teamer or testing component responsible for executing this test case.","nullable":true},"variation":{"type":"string","description":"Variation or specific configuration of the test case.","nullable":true},"status":{"type":"string","description":"Execution status indicating the outcome of the test case (e.g., 'passed', 'failed', 'error').","nullable":true},"redTeamerLabels":{"type":"object","additionalProperties":{"type":"string"},"description":"Optional labels or metadata provided by the red teamer for additional context.","nullable":true},"createdAt":{"type":"string","description":"Timestamp when the probe run result was created.","format":"date-time"},"conversation":{"type":"array","items":{"type":"array","items":{"$ref":"#/components/schemas/MessageV2Dto"}},"description":"Complete conversation transcript showing the interaction flow during the test case execution.","nullable":true},"explanation":{"type":"string","description":"Detailed explanation or analysis of the test case result and its implications.","nullable":true}},"additionalProperties":false,"description":"Individual Benchmark probe run result containing attack details, execution strategy, and conversations."},"MessageV2Dto":{"required":["messageContents","role"],"type":"object","properties":{"role":{"type":"string","nullable":true},"messageContents":{"type":"array","items":{"$ref":"#/components/schemas/ContentDto"},"nullable":true}},"additionalProperties":false},"ContentDto":{"required":["contentType"],"type":"object","properties":{"text":{"type":"string","nullable":true},"encodedText":{"type":"string","nullable":true},"imageUrl":{"type":"string","nullable":true},"encodedImageUrl":{"type":"string","nullable":true},"contentType":{"type":"string","nullable":true},"audioUrl":{"type":"string","nullable":true},"encodedAudioUrl":{"type":"string","nullable":true},"documentUrl":{"type":"string","nullable":true},"encodedDocumentUrl":{"type":"string","nullable":true}},"additionalProperties":false},"ErrorResponse":{"required":["error"],"type":"object","properties":{"error":{"oneOf":[{"$ref":"#/components/schemas/ErrorDetailsDto"},{"$ref":"#/components/schemas/BadRequestErrorDetailsDto"}],"description":"Error object."}},"additionalProperties":false,"description":"Response payload for error."},"ErrorDetailsDto":{"required":["message"],"type":"object","properties":{"message":{"type":"string","description":"Error detailed message."},"code":{"type":"string","description":"Error code."}},"additionalProperties":false},"BadRequestErrorDetailsDto":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorDetailsDto"}],"properties":{"validationErrors":{"type":"object","additionalProperties":{"type":"array","items":{"type":"string"}},"description":"Specific validation errors.","nullable":true}},"additionalProperties":false},"UnauthorizedError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Unauthorized access error."},"UnauthorizedWithLogoutError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Unauthorized access error."},"ForbiddenError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Forbidden access error."},"InternalServerError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Internal Server error."},"NotFoundExampleError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Not Found error."}}},"paths":{"/api/v2/benchmarks/models/{modelId}/runs/{probeRunId}/test-cases":{"get":{"tags":["BenchmarkV"],"summary":"Get details of a specific Benchmark probe run.","description":"Retrieve detailed information about a specific Benchmark probe run by its unique identifier, including results, execution metadata and conversation.","parameters":[{"name":"modelId","in":"path","required":true,"schema":{"type":"integer","format":"int64"}},{"name":"probeRunId","in":"path","required":true,"schema":{"type":"integer","format":"int64"}}],"responses":{"200":{"description":"OK","content":{"application/json":{"schema":{"$ref":"#/components/schemas/BenchmarkV2ProbeRunWithResultsDto"}}}},"400":{"description":"Bad Request","content":{"application/json":{"schema":{"oneOf":[{"$ref":"#/components/schemas/ErrorResponse"},{"$ref":"#/components/schemas/UnauthorizedError"},{"$ref":"#/components/schemas/UnauthorizedWithLogoutError"},{"$ref":"#/components/schemas/ForbiddenError"},{"$ref":"#/components/schemas/InternalServerError"},{"$ref":"#/components/schemas/NotFoundExampleError"}],"description":"Response payload for error."}}}},"401":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/UnauthorizedError"}}}},"403":{"description":"Forbidden","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ForbiddenError"}}}},"500":{"description":"Internal Server Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/InternalServerError"}}}}}}}}}
```

## Get all Benchmark types.

> Retrieve all available Benchmark types.

```json
{"openapi":"3.0.4","info":{"title":"API","version":"v1.0"},"tags":[{"name":"BenchmarkV","description":"The API provides endpoints for fetching data related to Benchmark and details about categories, types, models and probe runs."}],"servers":[{"url":"https://api.probe.splx.ai","description":"EU Server"},{"url":"https://us.api.probe.splx.ai","description":"US Server"}],"security":[{"API Key":[]}],"components":{"securitySchemes":{"API Key":{"type":"apiKey","description":"API Key for authentication","name":"X-Api-Key","in":"header"}},"schemas":{"BenchmarkTypeDto":{"required":["id","name"],"type":"object","properties":{"id":{"type":"integer","description":"Unique identifier for the Benchmark type.","format":"int32"},"name":{"type":"string","description":"Name of the Benchmark type.","nullable":true},"description":{"type":"string","description":"Additional context about the Benchmark type.","nullable":true}},"additionalProperties":false,"description":"Benchmark type information containing identification and description."},"ErrorResponse":{"required":["error"],"type":"object","properties":{"error":{"oneOf":[{"$ref":"#/components/schemas/ErrorDetailsDto"},{"$ref":"#/components/schemas/BadRequestErrorDetailsDto"}],"description":"Error object."}},"additionalProperties":false,"description":"Response payload for error."},"ErrorDetailsDto":{"required":["message"],"type":"object","properties":{"message":{"type":"string","description":"Error detailed message."},"code":{"type":"string","description":"Error code."}},"additionalProperties":false},"BadRequestErrorDetailsDto":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorDetailsDto"}],"properties":{"validationErrors":{"type":"object","additionalProperties":{"type":"array","items":{"type":"string"}},"description":"Specific validation errors.","nullable":true}},"additionalProperties":false},"UnauthorizedError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Unauthorized access error."},"UnauthorizedWithLogoutError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Unauthorized access error."},"ForbiddenError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Forbidden access error."},"InternalServerError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Internal Server error."},"NotFoundExampleError":{"type":"object","allOf":[{"$ref":"#/components/schemas/ErrorResponse"}],"additionalProperties":false,"description":"Response payload for Not Found error."}}},"paths":{"/api/v2/benchmarks/types":{"get":{"tags":["BenchmarkV"],"summary":"Get all Benchmark types.","description":"Retrieve all available Benchmark types.","responses":{"200":{"description":"OK","content":{"application/json":{"schema":{"type":"array","items":{"$ref":"#/components/schemas/BenchmarkTypeDto"}}}}},"400":{"description":"Bad Request","content":{"application/json":{"schema":{"oneOf":[{"$ref":"#/components/schemas/ErrorResponse"},{"$ref":"#/components/schemas/UnauthorizedError"},{"$ref":"#/components/schemas/UnauthorizedWithLogoutError"},{"$ref":"#/components/schemas/ForbiddenError"},{"$ref":"#/components/schemas/InternalServerError"},{"$ref":"#/components/schemas/NotFoundExampleError"}],"description":"Response payload for error."}}}},"401":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/UnauthorizedError"}}}},"403":{"description":"Forbidden","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ForbiddenError"}}}},"500":{"description":"Internal Server Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/InternalServerError"}}}}}}}}}
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.probe.splx.ai/platform-api/api-reference/benchmarks.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.