AddResultRequestSchema

custom_eval_setting_idstring

Numeric ID of the custom evaluation configuration this result belongs to.

Default: null

Example: 1001

data_lengthinteger

Number of evaluation examples included in this result batch.

Default: null

Example: 10

model_1_namestring

Name of the primary model whose score is being recorded.

Default: null

Example: Llama-3.3-70B-Instruct

model_1_scorenumber

Aggregate score for model 1 on this batch. Range: 0.0–1.0.

Default: null

Example: 0.75

model_2_namestring

Name of the baseline comparison model.

Default: null

Example: Mistral-Small-24B-Instruct-2501

model_2_scorenumber

Aggregate score for model 2 on this batch. Range: 0.0–1.0.

Default: null

Example: 0.7

org_idinteger

Organisation ID for scoping the evaluation result.

Default: null

pipeline_uuidstring

UUID of the evaluation pipeline this result belongs to.

Default: null

user_idinteger

ID of the user submitting the evaluation result.

Default: null

AddResultRequestSchema

{
  "custom_eval_setting_id": 1001,
  "model_1_name": "Llama-3.3-70B-Instruct",
  "model_2_name": "Mistral-Small-24B-Instruct-2501",
  "model_1_score": 0.75,
  "model_2_score": 0.7,
  "data_length": 10
}