NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KBXS1VTWFM6N50SHR3MSYC
Run Details
Model:
DeepSeek V4 Flash 0731 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
59.4s
Cost:
$0.000129
Provider:
Morph
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
29.16%
Dialogue to Total Word Ratio
(details)
14.5789%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
The inflatable bouncy castle hissed like a dying whale as Molly and Bill crouched behind the catering van. A dozen screaming children were doing their best to rupture eardrums fifty feet away. “Okay, walk me through it again,” Molly whispered, adjusting her neon-pink clown wig. “I’ve told you three times,” Bill grumbled, his fake red nose squeaking. “I cause a diversion with the balloon animals. You slip in during the ‘Pin the Tail’ chaos and empty the gift table.” “And the parents?” “They’re all watching the magic show. The magician is my cousin, Larry. He does a forty-minute sawing-a-lady-in-half bit—it’s really slow.” “Slow is good,” Molly mused, peeking over the van’s hood. “What about the birthday boy?” “He’s four. He’s eating cake with his hands. He doesn’t care about presents until the crying part starts.” “Right. And you’re sure no one will notice we’re not parents?” Bill gestured to his sweaty, oversized polo shirt. “I look like a dad who gives up. You look like a mom who drinks. We blend.” “I’m not drinking. I’m holding a juice box for cover.” “Same thing, Molly. Same thing.” A piercing shriek erupted from the party. Bill’s eyes widened. “That’s Larry. He’s on fire. He did it early. Go, go, go!” Molly sprinted, tripped over a tricycle, and face-planted into the pile of gifts. “Perfect timing,” she muttered, shoving a wrapped dinosaur into her shirt. Bill skidded up beside her, shooing a toddler. “Grab the unicorn. That’s worth at least forty bucks on the black market.”
created_at
"2026-09-03T10:09:41.448Z"
9/3/2026, 10:09:41 AM
model
"deepseek/deepseek-v4-flash-20260731"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1211
moderation_latency
(null)
generation_time
59316
tokens_prompt
75
tokens_completion
470
native_tokens_prompt
67
native_tokens_completion
441
native_tokens_completion_images
(null)
native_tokens_reasoning
49
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
0.000129214
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788430181-i3xzABWc4zrjnfO3tEKX"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788430181-k2MVofJ1zkY6eUwutMii"
upstream_id
"chatcmpl-3e74d943-097c-4e55-9477-7340887e43bf"
provider_responses
0
endpoint_id
"fc1cac03-9834-4ed8-8dfe-2dfb8543b690"
id
"chatcmpl-3e74d943-097c-4e55-9477-7340887e43bf"
is_byok
false
latency
1211
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"Morph"
status
200
total_cost
0.000129214
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Morph"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
254
29.16%
Dialogue to Total Word Ratio
Ratio: 60.54%, Deviation: 10.54%
neededClean
false
wordsTotal
261
wordsDialogue
158
14.5789%