NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2J9B2GDEACGZ6AXT3F9N5K
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.0s
Cost:
$0.000113
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
0.89%
Dialogue to Total Word Ratio
(details)
43.6375%
Overall
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 adjusted the strap of her duffel bag, eyeing the inflatable bounce house with professional disdain. Bill crouched behind a hedge, his balaclava bunched around his neck like a nervous turtleneck. “This is insane,” Bill said, earning a sharp elbow from Molly. “Shut it,” she whispered. “The piñata’s our Trojan horse.” A child shrieked past, clutching a glitter-wrapped box. Molly’s fingers twitched. Bill tugged at his collar. “We’re stealing from kids.” “We’re redistributing. That little monster has enough Legos.” She pointed to the gift table, a fortress of pastel paper and ribbon. The plan was simple: replace the real presents with decoy boxes, slip out during the chaos of cake time. Bill nodded slowly, then stopped. “I’m not wearing the clown suit.” “You’ll wear the suit.” Molly unrolled a pair of oversized shoes. “Or you’re the distraction.” A mother turned, frowning at the hedge. Molly flashed a placid smile, arm around Bill. “Just discussing the treasure hunt,” she sang. The mother wandered off. Bill sighed. “Fine. But I keep the horn.” Molly shook her head, already cataloguing loot. Ten percent of one hundred children’s joy—easy math, lighter conscience.
created_at
"2026-04-25T14:56:48.216Z"
4/25/2026, 2:56:48 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
696
moderation_latency
(null)
generation_time
5819
tokens_prompt
77
tokens_completion
424
native_tokens_prompt
67
native_tokens_completion
369
native_tokens_completion_images
(null)
native_tokens_reasoning
82
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"
usage
0.0001127
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"01b780b7-0215-4d9c-bcf4-f650f70a3fc6"
is_byok
false
latency
297
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepSeek"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777129008-pReHHib1D3DwTHvPrG8q"
session_id
(null)
api_type
"completions"
id
"gen-1777129008-2iCthhazqZbKjzr37fTa"
upstream_id
"01b780b7-0215-4d9c-bcf4-f650f70a3fc6"
total_cost
0.0001127
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
189
0.89%
Dialogue to Total Word Ratio
Ratio: 24.74%, Deviation: 14.74%
neededClean
false
wordsTotal
190
wordsDialogue
47
43.6375%