NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KA9GGGWQM6H86D37Q2KNTW
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
29.3s
Cost:
$0.012912
Provider:
BaseTen
Evaluation summary
Score
Evaluator
Details Link
92.13%
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 sat silent beneath a bruised November sky, its windows dark and unwelcoming as the first guests arrived. Detective Inspector Clara Vane stepped from her car and studied the sprawling estate with narrowed eyes before approaching the door. A constable met her on the gravel drive, his face pale beneath the brim of his hat and uniform collar. "You'll want to see this, ma'am," he said quietly, turning toward the dimly lit conservatory at the back of the house. Inside, the air smelled of damp earth and spilled wine, and a single lamp flickered near the body on the floor. A woman in a crimson evening gown lay crumpled beside the overturned table, her eyes fixed open and utterly vacant. Clara knelt carefully, noting the single stab wound beneath the ribs and the strange absence of blood on her dress. The constable whispered, "The door was locked from the inside, Inspector, and every window is sealed with fresh white paint." Clara looked at the locked door, then at the dead woman, and felt the first cold prickle of suspicion rising. "Then someone in this house is lying," she said, "because no one vanishes from a sealed room without leaving traces."
created_at
"2026-09-03T09:41:08.767Z"
9/3/2026, 9:41:08 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
9136
moderation_latency
(null)
generation_time
29206
tokens_prompt
46
tokens_completion
3238
native_tokens_prompt
119
native_tokens_completion
3221
native_tokens_completion_images
(null)
native_tokens_reasoning
2964
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
0.01291224
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788428468-Yok88sPbO3ypLQGcPCCM"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788428468-ZzCMxC53P17UwvRQlE0B"
upstream_id
"chatcmpl-8bcb09bb6d554fafa64001e70332fc70"
provider_responses
0
endpoint_id
"85bb5a4a-983d-4d11-b97b-c7e5b348375f"
id
"chatcmpl-8bcb09bb6d554fafa64001e70332fc70"
is_byok
false
latency
9136
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"BaseTen"
status
200
total_cost
0.01291224
cache_discount
(null)
upstream_inference_cost
0
provider_name
"BaseTen"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
92.13%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
20
1
20
2
20
3
21
4
21
5
20
6
20
7
20
8
20
9
20