NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KBNA5HNTJXC46BSZJQ4TRN
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m
Cost:
$0.016684
Provider:
GMICloud
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3940%
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
"Bill, I've cased the bouncy castle. The presents are under the cake table." "Under the cake table? Surrounded by five-year-olds hopped up on fizzy juice?" "Exactly. They'll be distracted by Pin the Tail on the Donkey." "Pin the Tail? Last time I got near a donkey, I left with a hoof print." "That's because you tried to ride it. This is a paper donkey." "Paper can still cut. What's the plan?" "We dress as party clowns. I'll make balloon animals, you trip over the piñata." "Why am I always the piñata guy?" "Because you have the reflexes of a caffeinated squirrel. While they laugh, I slide the gifts into my clown car." "You drive a clown car?" "I hot-wired one from the circus. It seats eight, but the trunk's tiny." "How many presents?" "Seventeen. Mostly Legos and one heavy box labeled 'Grandma.'" "I don't steal from grandmas." "It's from Grandma, not for Grandma. Relax." "Fine. But I'm not wearing floppy shoes." "Bill, the shoes are non-negotiable. They squeak." "That's the problem." "No, squeaky shoes are scientifically proven to make children laugh." "Scientifically by who?" "By me. Are you in?" "I'm in. But if I step on Lego, I keep it."
created_at
"2026-09-03T10:05:04.065Z"
9/3/2026, 10:05:04 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2738
moderation_latency
(null)
generation_time
60385
tokens_prompt
75
tokens_completion
3978
native_tokens_prompt
146
native_tokens_completion
4908
native_tokens_completion_images
(null)
native_tokens_reasoning
4607
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
0.01668414
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788429904-73yz1mDHNsILW3DDIg7s"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788429904-FUBPSQbDuf4tDXmVNQr2"
upstream_id
"0afa6a38-1031-4d8a-91b7-67c24d2e9ce3"
provider_responses
0
endpoint_id
"a11bdcb9-acb5-49df-9ff5-8c1486186664"
id
"0afa6a38-1031-4d8a-91b7-67c24d2e9ce3"
is_byok
false
latency
2738
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"GMICloud"
status
200
total_cost
0.01668414
cache_discount
(null)
upstream_inference_cost
0
provider_name
"GMICloud"
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
200
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
204
wordsDialogue
204
68.3940%