NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KC8C812GDJN3646ZGYDQKG
Run Details
Model:
DeepSeek V4 Flash 0731 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 18s
Cost:
$0.000211
Provider:
CoreWeave
Evaluation summary
Score
Evaluator
Details Link
1.04%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.5180%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Molly spread the blueprint across the sticky kitchen table. "Okay, so the plan is simple." Bill stared at the crudely drawn diagram. "A birthday party? You want us to rob a bunch of five-year-olds?" "Not rob. Liberate. And it's not a bunch, it's the Henderson twins. Trust fund babies. Their presents are worth more than my car." "I'm not stealing from kids, Moll. That's a new low, even for us." "It's not stealing. It's a strategic redistribution. And they're not 'kids,' they're tiny billionaires. Look, I've got the layout. Bounce house, craft table, snack corner, and the gift table right next to the cake. Easy in, easier out." "So what's our angle? We dress up as clowns? We sneak in as the entertainment?" "Better. We're the parents of Tommy." "There's no Tommy." "Exactly. We show up, we act entitled, we complain about the gluten in the cupcakes. While you're distracting the mom, I grab the gift bags and slip out the back." "And what do I do, scream about a gluten allergy?" "Yes, but make it dramatic. Cry a little. Mention your chiropractor." Bill sighed, rubbing his temples. "Fine. But I'm keeping a coloring book." Molly grinned. "Deal. Now, how do you feel about balloon animals?" "I feel like I'm going to jail." "That's the spirit. Now, practice this face: 'I demand to see the manager.'"
created_at
"2026-09-03T10:15:28.783Z"
9/3/2026, 10:15:28 AM
model
"deepseek/deepseek-v4-flash-20260731"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6550
moderation_latency
(null)
generation_time
78005
tokens_prompt
75
tokens_completion
686
native_tokens_prompt
146
native_tokens_completion
687
native_tokens_completion_images
(null)
native_tokens_reasoning
359
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
0.00021134
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788430528-Xy3GPzRE9klTfjjOB6mf"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788430528-Fsu9QES1HulEPCijIoR2"
upstream_id
"chatcmpl-ff333565-d794-45b4-acfb-8b50faa6a7f6"
provider_responses
0
endpoint_id
"cbfecbd7-9a18-45ea-bcd1-fabaa868db5c"
id
"chatcmpl-ff333565-d794-45b4-acfb-8b50faa6a7f6"
is_byok
false
latency
656
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"CoreWeave"
status
200
total_cost
0.00021134
cache_discount
(null)
upstream_inference_cost
0
provider_name
"CoreWeave"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
1.04%
Matches word count
n/a
neededClean
false
words
226
0.00%
Dialogue to Total Word Ratio
Ratio: 89.91%, Deviation: 39.91%
neededClean
false
wordsTotal
228
wordsDialogue
205
0.5180%