NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KA1714H3EZ22T8BV4QNHEA
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
40.2s
Cost:
$0.013299
Provider:
SiliconFlow
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 20 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The old manor's library smelled of damp wool and candle smoke, and heavy shadows gathered beneath the sagging oak bookshelves. Detective Marlowe found the body slumped in a leather wingback chair, a single crimson rose resting upon its still lap. The victim's eyes were wide open, staring at the ornate ceiling as though she had witnessed something utterly impossible there. A porcelain teacup lay shattered near the cold fireplace, and a faint trace of bitter almonds lingered in the air. There was no blood, no visible wound, and no sign of struggle, only the clock ticking loudly from the mantel. Marlowe noticed a folded note tucked beneath the rose, its edges crisp and white against the dark velvet chair fabric. He carefully lifted the note with gloved fingers, unfolded it, and read the single typed line printed in black ink. The message said, "You missed one, Detective," and below it was a tiny drawing of a clock stopped at midnight.
created_at
"2026-09-03T09:36:36.915Z"
9/3/2026, 9:36:36 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
917
moderation_latency
(null)
generation_time
40172
tokens_prompt
46
tokens_completion
3258
native_tokens_prompt
118
native_tokens_completion
3319
native_tokens_completion_images
(null)
native_tokens_reasoning
3125
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
0.013299
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788428196-hf3IFP01kTjsXRhZNn3Z"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788428196-QI2oPemRutSz8P3KqD37"
upstream_id
"chatcmpl-ef62f580-80c7-47c6-82d8-48d0f772f0bd"
provider_responses
0
endpoint_id
"65367950-3b6c-4abd-9cb0-d553a47de6d9"
id
"chatcmpl-ef62f580-80c7-47c6-82d8-48d0f772f0bd"
is_byok
false
latency
917
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"SiliconFlow"
status
200
total_cost
0.013299
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
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
8
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
20