NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2JSC4EEFFRAKFV4D5C3EPB
Run Details
Model:
DeepSeek V4 Flash
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
2.9s
Cost:
$0.000043
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
69.16%
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 rain-slicked cobblestones gleamed under the dim streetlight. A woman's scream pierced the quiet midnight air. Detective Harding paused, his coffee cup halfway to his lips. He turned toward the sound, dread pooling in his stomach. The alley yawned darkly between two shadowed brick buildings. A single leather glove lay crumpled near the gutter. Harding approached slowly, his footsteps echoing on wet stone. The body was propped against a rain-soaked wall. A crimson ribbon trailed from her pale, still wrist. He knelt, noting the absence of any visible wounds. Above, a flickering neon sign hummed its weary, broken song.
created_at
"2026-04-25T15:05:33.586Z"
4/25/2026, 3:05:33 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
618
moderation_latency
(null)
generation_time
2844
tokens_prompt
46
tokens_completion
157
native_tokens_prompt
39
native_tokens_completion
135
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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"
usage
0.00004326
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"11c0c465-5c88-4ed0-9d5f-47c4da964b1c"
is_byok
false
latency
272
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepSeek"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777129533-ZdQHT6LRVp8GXEagM5fL"
session_id
(null)
api_type
"completions"
id
"gen-1777129533-Dwo4cl790dylQ44YjvlM"
upstream_id
"11c0c465-5c88-4ed0-9d5f-47c4da964b1c"
total_cost
0.00004326
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
69.16%
Matches word count
n/a
neededClean
false
sentences
11
wordCounts
0
8
1
8
2
10
3
10
4
9
5
9
6
9
7
8
8
9
9
9
10
10