NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5GB5816SV9MRAKG8BZVE5
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.9s
Cost:
$0.000267
Provider:
SiliconFlow
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly traced a chubby crayon line on the map, which was actually a crude drawing of a bouncy castle next to a plate of biscuits. Bill leaned over her shoulder, his breath smelling faintly of cheese and onion crisps. “The target is heavily guarded,” Molly murmured, her eyes narrowing at a stick-figure labeled ‘Sharon (Vigilante Mom)’. “Perimeter is soft, but the patter of tiny feet creates unpredictable foot traffic.” Bill nodded grimly, tapping a spot marked ‘X’. “The loot will be concentrated here, under the ceremonial cake. We go in during the peak distraction.” “Which is?” “The piñata massacre. Maximum chaos.” He squinted at the map. “Extraction via slip-and-slide?” Molly shook her head. “Too risky. We’d get soggy. No, we use the garden gnome as a marker, exit through the hedge.” She folded the map with finality. The two master thieves sat in silence, the gravity of their mission settling over the dimly lit shed. They were going to rip off a six-year-old’s birthday party, and the stakes had never been so aggressively cheerful.
created_at
"2026-02-16T21:25:48.33616+00:00"
2/16/2026, 9:25:48 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1625
moderation_latency
(null)
generation_time
12871
tokens_prompt
95
tokens_completion
286
native_tokens_prompt
70
native_tokens_completion
248
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
0.0002669
router
(null)
provider_responses
0
id
"019c685830ba93330e4b73da3f498fa8"
status
200
is_byok
false
latency
1598
endpoint_id
"5d5c9c1d-af0d-4e4a-8aee-c5cd2b3883f3"
provider_name
"SiliconFlow"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277135-ETSHx2ZoGO8ZT4xAu1yu"
upstream_id
"019c685830ba93330e4b73da3f498fa8"
total_cost
0.0002669
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
Evaluation details
Result
Evaluator
Details
Meta Data
14.3014%
Matches word count
n/a
neededClean
false
words
179
0.0000%
Dialogue to Total Word Ratio
Ratio: 38.55%, Deviation: 28.55%
neededClean
false
wordsTotal
179
wordsDialogue
69
7.1507%