NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KBAKX22FYH24YCNDJ95XTW
Run Details
Model:
DeepSeek V4 Flash 0731 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
52.6s
Cost:
$0.002070
Provider:
Makora
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9975%
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 flattened the glittered invitation against the dash, her nose wrinkling at the scent of vanilla and play-doh. The plan was deceptively simple: infiltrate the suburban birthday party, bypass the bouncy castle, and liberate the mountain of wrapped presents stacked under the pergola. Bill, however, was having moral qualms. He adjusted his fake mustache, which was shedding glitter. "We're stealing from children, Molly." That was his entire contribution. Molly didn't look up from her schematics, a crayon-drawn map of the backyard. "The Pinata is a decoy," she said, tapping the spot labeled 'Gift Table'. Bill sighed, pocketing a single, sparkly sticker he'd already swiped. "I call the dinosaur." She nodded, checking her watch. They had three minutes before the cake was served, when every sticky-handed toddler would be distracted. They crawled through the hedge, silent as clowns in socks, toward the laughter and the wrapping paper. As they reached the edge of the lawn, Bill froze. "Duck behind the bouncy castle." Molly obeyed, crouching behind the inflatable structure. The glitter on the invitation had transferred to her cheek, and she looked like a deranged fairy godmother. "Duck," Bill repeated, pointing at a woman with a camera. She winked at him.
created_at
"2026-09-03T09:59:13.584Z"
9/3/2026, 9:59:13 AM
model
"deepseek/deepseek-v4-flash-20260731"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
456
moderation_latency
(null)
generation_time
51218
tokens_prompt
75
tokens_completion
9433
native_tokens_prompt
67
native_tokens_completion
10587
native_tokens_completion_images
(null)
native_tokens_reasoning
9115
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
0.002070495
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788429553-RX4PdbWTP6YvoJXthHSN"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788429553-30q5ETLTFUQ3H58b1uD5"
upstream_id
"chatcmpl-a0d0330c-fd4a-4155-80f9-0cde64895689"
provider_responses
0
endpoint_id
"f954a48e-1c90-433b-9348-4720f8030331"
is_byok
false
latency
167
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"OpenInference"
status
429
1
endpoint_id
"14c4df90-c7af-42ff-99e7-69d62a89e7d5"
is_byok
false
latency
1125
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"AkashML"
status
429
2
endpoint_id
"562d5188-97d1-49f7-8881-d0e417e31ada"
id
"chatcmpl-a0d0330c-fd4a-4155-80f9-0cde64895689"
is_byok
false
latency
128
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"Makora"
status
200
total_cost
0.002070495
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Makora"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.84%, Deviation: 0.84%
neededClean
false
wordsTotal
203
wordsDialogue
22
99.9975%