Sign in

v2

latestOpenAPI 3.1.02026-08-05267431678.1 KB
felix

Start Benchmark Evaluation

Start an asynchronous benchmark evaluation.

Launches evaluation in the background and returns immediately with an evaluation_id that can be used to check status.

post/felix/benchmarks/evaluate

Request body

model_idstring required

Training job ID, explicit GLiNER base model ID ('fastino/gliner2-base-v1'), or decoder base model ID ('base:{hf_model_id}')

project_idstring nullable

Optional project ID to associate the benchmark evaluation with

task'ner' | 'text_classification' required

Task type for evaluation

benchmarkstring required

Benchmark name (e.g., 'fewnerd', 'mteb/banking77', 'tweeteval')

max_samplesinteger

Maximum samples to evaluate

splitstring

Dataset split to use

benchmark_configobject nullable

Additional benchmark-specific configuration

Response

Successful Response

successboolean required
evaluation_idstring required
project_idstring nullable
status'pending' | 'running' | 'complete' | 'failed' | 'cancelled' required
taskstring required
benchmarkstring required
model_idstring required
metricsobject nullable
error_messagestring nullable
created_atstring date-time required
completed_atstring date-time nullable