NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KAKFXE6V6FW9NBYX7N1WPN
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
3m 54s
Cost:
$0.054779
Provider:
DigitalOcean
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 10 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The old manor glowed faintly under the heavy evening rain. Detective Mara Voss stepped from her unmarked car, collar raised. A single light burned in the library's tall arched window. The front door stood open, swaying with the wet wind. She stepped inside, finding the marble floor slick with rain. A grandfather clock ticked slowly somewhere in the dark hall. Then Mara heard a wet cough from the library door. She drew her flashlight, moving toward the sound without speech. The library door hung crooked from one bent brass hinge. Inside, an overturned armchair lay beside a shattered crystal decanter. A woman's body sprawled by the dead fireplace, throat cut. Mara knelt beside her, pressing two fingers to the neck. The flesh was cooling, but a faint pulse still beat. The woman coughed blood and whispered a single word: "Cellar."
created_at
"2026-09-03T09:46:35.84Z"
9/3/2026, 9:46:35 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
531
moderation_latency
(null)
generation_time
234302
tokens_prompt
46
tokens_completion
16800
native_tokens_prompt
39
native_tokens_completion
13820
native_tokens_completion_images
(null)
native_tokens_reasoning
13653
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
0.05477868
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788428795-ta64b89dL4eCKTuZFMk8"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788428795-pzjslkraHWG0rcKxdnCM"
upstream_id
"chatcmpl-4e6bf399-c805-46e9-a801-9aa281c8ef64"
provider_responses
0
endpoint_id
"928ab2e9-a85f-427f-adcb-15b2394c70d5"
id
"chatcmpl-4e6bf399-c805-46e9-a801-9aa281c8ef64"
is_byok
false
latency
518
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"DigitalOcean"
status
200
total_cost
0.05477868
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DigitalOcean"
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
sentences
14
wordCounts
0
10
1
10
2
10
3
10
4
10
5
10
6
10
7
10
8
10
9
10
10
10
11
10
12
10
13
10