NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5QGXR7PA9XSSR3EE0V8NA
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
4.1s
Cost:
$0.000115
Provider:
AtlasCloud
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 glass shattered at midnight, sprayinThe rain tapped softly on the windows, hiding the footsteps creeping up the creaky staircase outside the old townhouse. A shadow slipped through the cracked door, its breath shallow and gloved hands clutching something dark and metallic. Blood pooled beneath the body, still warm, as the clock struck one with a hollow, echoing chime. The detective arrived ten minutes later, his sharp eyes scanning the room for clues the killer had left behind. A single playing card—the ace of spades—lay face-up on the table, mocking him with its silent smirk.
created_at
"2026-02-16T21:29:35.069325+00:00"
2/16/2026, 9:29:35 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
804
moderation_latency
(null)
generation_time
4033
tokens_prompt
46
tokens_completion
149
native_tokens_prompt
39
native_tokens_completion
121
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.000114796
router
(null)
provider_responses
0
id
"b663720c4022455d9db4e0283bf129f0"
status
200
is_byok
false
latency
804
endpoint_id
"5bb598f5-fd97-4f8b-91e4-ceab3743a03b"
provider_name
"AtlasCloud"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277370-E5ceDtSWpmuAunBWyLVl"
upstream_id
"b663720c4022455d9db4e0283bf129f0"
total_cost
0.000114796
cache_discount
1.08e-7
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
35.0662%
Matches word count
n/a
neededClean
false
sentences
5
wordCounts
0
24
1
18
2
17
3
19
4
20