NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KAY3XQ43J1YXH4P3JH8R4D
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
1m 15s
Cost:
$0.022260
Provider:
StreamLake
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 storm drowned the manor's lights just as Detective Inspector Hale crossed the iron gate with his collar turned high. A constable met him beneath the portico, his flashlight trembling as thunder rolled across the black Devonshire hills that night. "She is in the library, sir," the young officer whispered, and Hale noticed a smear of blood on his cuff. They passed through a candlelit hall where old portraits seemed to lean inward, their painted eyes following the two men. The library door stood open, and the smell of wet wool, paraffin, and something metallic coiled around them like smoke. A woman in a silver evening gown lay face down on the Persian rug, one pale hand clutching a pen. Hale knelt beside her and tilted his head, studying the small wound now hidden beneath her pearl earring's broken clasp. No weapon lay in sight, yet the window behind her was bolted shut inside; its key still sat there waiting. The constable whispered that the household had gathered in the dining room, all twelve guests accounted for and deeply silent. Hale stood, glancing at the pen in her hand, and asked whose name she had been writing when she died.
created_at
"2026-09-03T09:52:24.002Z"
9/3/2026, 9:52:24 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1657
moderation_latency
(null)
generation_time
75176
tokens_prompt
46
tokens_completion
6437
native_tokens_prompt
118
native_tokens_completion
6613
native_tokens_completion_images
(null)
native_tokens_reasoning
6374
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
0.022260037
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788429144-P5Jwml1KIA233bldcTCF"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788429144-feKg5WFFvo1KRv4fwxZo"
upstream_id
"req-33hg0z-1788429144185871622"
provider_responses
0
endpoint_id
"072c1c23-c069-4242-bb6d-1b30ca5f4eb8"
id
"req-33hg0z-1788429144185871622"
is_byok
false
latency
1657
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"StreamLake"
status
200
total_cost
0.022260037
cache_discount
(null)
upstream_inference_cost
0
provider_name
"StreamLake"
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
10
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
20
8
20
9
20