NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-20-01M5C6GYCRVYBEDGK80BNM98FA
Run Details
Model:
DeepSeek V4.1 Flash 1017 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
21.1s
Cost:
$0.001667
Provider:
InferenceNet
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9995%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
"Okay," Molly said, "the clown's distracted the toddlers with a balloon animal. We've got ninety seconds." "Ninety? I need two minutes just to untangle the ribbon on that giant teddy bear," Bill said. "Then skip the bear. Grab the Lego set and the gift cards." "Gift cards? For a five-year-old? That's low, even for us." "Low is a pile of presents in the back of a van. Now move." "Wait—what if the birthday boy cries?" "Bill, we're thieves, not monsters. He'll cry either way. Focus." "But his mom's got a camera." "So smile and wave. You're wearing a dinosaur mask." "This mask smells like feet." "Less sniffing, more snatching. The piñata's about to break—that's our cue." "Fine. But I'm keeping the stuffed unicorn." "No, you're not. That's evidence." "It's fluffy evidence." "And the glitter gun." "No." "Please?" "Fine, but you carry it." "Bill!" "Okay, okay. On three?" "On three. And don't trip over the bouncy castle this time." "That was one time." "One time too many. Go!" "Wait, the goody bags!" "Forget the goody bags!" "But they have tiny yo-yos." "Deal?" "Deal." They crept toward the party tent. The clown honked a horn. Bill adjusted his mask. Molly grinned.
created_at
"2026-10-20T08:23:24.318Z"
10/20/2026, 8:23:24 AM
model
"deepseek/deepseek-v4.1-flash-20261017"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
159
moderation_latency
(null)
generation_time
21073
tokens_prompt
75
tokens_completion
2807
native_tokens_prompt
67
native_tokens_completion
3323
native_tokens_completion_images
(null)
native_tokens_reasoning
3006
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
service_tier
(null)
usage
0.00166686
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1792484604-cynAQ58hf45LSueeEztP"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1792484604-Kkd91aUkOtray5T1LsRC"
upstream_id
"gv2_CDFJqy7sAPO2eVN5HqSCu"
provider_responses
0
endpoint_id
"4231aea9-73af-4a2f-bd14-660b1d8b13b2"
id
"gv2_CDFJqy7sAPO2eVN5HqSCu"
is_byok
false
latency
159
model_permaslug
"deepseek/deepseek-v4.1-flash-20261017"
provider_name
"InferenceNet"
status
200
total_cost
0.00166686
cache_discount
(null)
upstream_inference_cost
0
provider_name
"InferenceNet"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
201
100.00%
Dialogue to Total Word Ratio
Ratio: 89.71%, Deviation: 0.29%
neededClean
false
wordsTotal
204
wordsDialogue
183
99.9995%