Run: 2026-02-25-01KJBG3HEXMP42H5Y66ABQCMMH

Run Details

Model:
Qwen 3.5 35B
Test:
Data extraction
Scenario:
All valid emails
Duration:
5.1s
Cost:
$0.001229
Provider:
Alibaba

Evaluation summary

Score Evaluator
Details Link
Pass Contains a list of texts (details)

Model input

User/Human
Extract all valid email addresses from the text. Return them in a comma-separated list without spaces. Contact information: 1. John Doe - john.doe@example.com 2. Jane Smith - jane@smith-family.net 3. support@company.co.uk 4. info@subdomain.example.org 5. Invalid email: not.an.email.com 6. Another invalid: @missing-username.com

Model response

AI
john.doe@example.com,jane@smith-family.net,support@company.co.uk,info@subdomain.example.org
created_at"2026-02-25T22:53:21.767Z" 2/25/2026, 10:53:21 PM
model"qwen/qwen3.5-35b-a3b-20260224"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency438
moderation_latency(null)
generation_time5038
tokens_prompt89
tokens_completion538
native_tokens_prompt93
native_tokens_completion603
native_tokens_completion_images(null)
native_tokens_reasoning574
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.00122925
router(null)
provider_responses
0
endpoint_id"48c1210f-b7d2-4688-a340-f7424fc99d2b"
id"chatcmpl-3ed0a7a1-785a-9429-8a0b-0fe70739ed92"
is_byokfalse
latency438
model_permaslug"qwen/qwen3.5-35b-a3b-20260224"
provider_name"Alibaba"
status200
api_type"completions"
id"gen-1772060001-2QayOH9rR4PLFLttRFgc"
upstream_id"chatcmpl-3ed0a7a1-785a-9429-8a0b-0fe70739ed92"
total_cost0.00122925
cache_discount(null)
upstream_inference_cost0
provider_name"Alibaba"

Evaluation details

Result Evaluator Details Meta Data
Pass Contains a list of texts
john.doe@example.com jane@smith-family.net support@company.co.uk info@subdomain.example.org
john.doe@example.comtrue
jane@smith-family.nettrue
support@company.co.uktrue
info@subdomain.example.orgtrue