NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KCHGPRD9DMMV6J19DW89H0
Run Details
Model:
DeepSeek V4 Flash 0731 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4m 20s
Cost:
$0.004315
Provider:
Mancer 2
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 and Bill crouched behind a hedge, watching the garden party explode with children. The lawn was a chaos of streamers, screaming, and a bouncy castle that quivered under a swarm of six-year-olds. Bill scratched his fake beard, dislodging a flake of foam. "The presents are by the magician." Molly adjusted her sunglasses, scanning the layout. She had a plan: Bill would trip the caterer, sending a tray of cupcakes airborne. In the chaos, she'd swap the gift bag with one full of bricks. "Why bricks?" he whispered. "Weight." Bill sneezed. He was allergic to the pony rides, the glitter, and the sheer volume of screaming. His eyes watered instantly. Molly handed him a tissue. "You're the distraction." Bill paled. "I'm the distraction?" He looked at the children, the clown, and the giant unicorn piƱata. The magician was pulling a rabbit from a hat, and the birthday girl was crying because the rabbit was missing an ear. "I'd rather take the bricks." Molly grinned. Then she shoved him onto the bouncy castle. He bounced once, twice, and then disappeared into the pile of flailing limbs. The clown tried to blow a whistle but only produced a sad, rubbery little squeak.
created_at
"2026-09-03T10:20:28.263Z"
9/3/2026, 10:20:28 AM
model
"deepseek/deepseek-v4-flash-20260731"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1357
moderation_latency
(null)
generation_time
255980
tokens_prompt
75
tokens_completion
7073
native_tokens_prompt
146
native_tokens_completion
8581
native_tokens_completion_images
(null)
native_tokens_reasoning
6777
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
0.004315
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788430828-NnUXD1rGvGndlmWoQEXA"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788430828-EmYteDzhhHEk1EfSSive"
upstream_id
"01a066c8d2c00020"
provider_responses
0
endpoint_id
"57c1bfab-049c-4d6a-ab34-ac1007a6043b"
is_byok
false
latency
3736
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"Relace"
status
429
1
endpoint_id
"562d5188-97d1-49f7-8881-d0e417e31ada"
is_byok
false
latency
58
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"Makora"
status
429
2
endpoint_id
"9c83b6fb-0614-4d50-b30b-123a09ba354a"
id
"01a066c8d2c00020"
is_byok
false
latency
859
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"Mancer 2"
status
200
total_cost
0.004315
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mancer 2"
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: 9.90%, Deviation: 0.10%
neededClean
false
wordsTotal
202
wordsDialogue
20
100.0000%