Run: 2026-02-16-01KHM5NGV112REEZ8H9DZ095RV

Run Details

Model:
DeepSeek V3.2
Test:
Data extraction
Scenario:
All valid emails
Duration:
18.3s
Cost:
$0.000369
Provider:
SiliconFlow

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"2026-02-16T21:28:43.856372+00:00" 2/16/2026, 9:28:43 PM
model"deepseek/deepseek-v3.2-20251201"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2652
moderation_latency(null)
generation_time18281
tokens_prompt89
tokens_completion781
native_tokens_prompt91
native_tokens_completion819
native_tokens_completion_images(null)
native_tokens_reasoning794
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"
usage0.00036855
router(null)
provider_responses
0
id"019c685ac51974bd4f17b8cc323e2e8a"
status200
is_byokfalse
latency2651
endpoint_id"b39a588a-b338-43ba-b046-226b9e24afa8"
provider_name"SiliconFlow"
model_permaslug"deepseek/deepseek-v3.2-20251201"
api_type"completions"
id"gen-1771277304-jyXV7RcmNQvhj4ejK5Ly"
upstream_id"019c685ac51974bd4f17b8cc323e2e8a"
total_cost0.00036855
cache_discount(null)
upstream_inference_cost0
provider_name"SiliconFlow"

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