AI Benchmark Claim Normalizer
Pricing
from $20.00 / 1,000 normalized claims
Normalize structured AI benchmark claims and produce evidence-backed comparability refusals when versions, splits, metrics, prompts, shots, or model settings do not align.
You can access the AI Benchmark Claim Normalizer programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1from apify_client import ApifyClient2
3# Initialize the ApifyClient with your Apify API token4# Replace '<YOUR_API_TOKEN>' with your token.5client = ApifyClient("<YOUR_API_TOKEN>")6
7# Prepare the Actor input8run_input = { "claims": [{9 "claimId": "demo-1",10 "source": {11 "url": "https://flintglade-tools.github.io/apify-fixtures/benchmarks/demo.html",12 "locator": "#claim-1",13 },14 "model": {15 "name": "ExampleModel",16 "revision": "abc123",17 },18 "benchmark": {19 "name": "ExampleBench",20 "version": "1.0",21 "split": "test",22 },23 "metric": {24 "name": "accuracy",25 "value": "0.812",26 "unit": "fraction",27 "direction": "higher_is_better",28 },29 "protocol": {30 "shots": 0,31 "promptTemplate": "fixture-v1",32 },33 }] }34
35# Run the Actor and wait for it to finish36run = client.actor("flintglade/ai-benchmark-claim-normalizer").call(run_input=run_input)37
38# Fetch and print Actor results from the run's dataset (if there are any)39print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])40for item in client.dataset(run["defaultDatasetId"]).iterate_items():41 print(item)42
43# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-startThe Apify API client for Python is the official library that allows you to use AI Benchmark Claim Normalizer API in Python, providing convenience functions and automatic retries on errors.
Install the apify-client
$pip install apify-clientOther API clients include: