NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1GRHH0NF8XBCMFA9767NNM
Run Details
Model:
Inception Mercury
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
4.4s
Cost:
$0.000204
Provider:
Inception
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.76%
Dialogue to Total Word Ratio
(details)
99.8789%
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 moon hung low over the suburban cul-de-sac, casting a silver glow on the modest house that hosted the annual birthday bash. Inside, balloons bobbed lazily, and the scent of frosting drifted through the open windows. Molly and Bill, both seasoned thieves with a knack for mischief, crouched in the shadows of the backyard, their eyes darting to the child's bedroom where the presents lay piled high. They exchanged glances, each knowing the other’s hesitation, and prepared to execute their audacious plan. They rehearsed the timing, noting the security guard’s shift changes, and plotted a silent exit route through backdoor. Molly: "So, Bill, the kids are distracted by the cake, right? We just need to slip in through the backdoor and grab the presents before the parents even notice." Bill: "Exactly, Molly. I’ve rehearsed the timing; I can sneak past the guard’s watch. I’ll have a backup plan—if the security system goes off, I’ll use the garden hose as a distraction." Molly: "Great! And we’ll leave the party with a giant balloon as our getaway flag. The kids won’t even know we were there." Bill: "Perfect. Let’s do it. We’ll be like ninjas, but with glitter and cake crumbs now."
created_at
"2026-03-06T12:08:07.463Z"
3/6/2026, 12:08:07 PM
model
"inception/mercury"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4288
moderation_latency
(null)
generation_time
4394
tokens_prompt
77
tokens_completion
314
native_tokens_prompt
72
native_tokens_completion
268
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
65
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
0.000204375
router
(null)
provider_responses
0
endpoint_id
"da1082ea-721e-460e-b330-034ae7aefc7f"
id
"chatcmpl-faed0eab-3a6b-405b-b890-26e23007b3cf"
is_byok
false
latency
55
model_permaslug
"inception/mercury"
provider_name
"Inception"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1772798887-bmH4sKztDnkQ1ehkp0Js"
upstream_id
"chatcmpl-faed0eab-3a6b-405b-b890-26e23007b3cf"
total_cost
0.000204375
cache_discount
0.000014625
upstream_inference_cost
0
provider_name
"Inception"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
201
99.76%
Dialogue to Total Word Ratio
Ratio: 47.78%, Deviation: 2.22%
neededClean
false
wordsTotal
203
wordsDialogue
97
99.8789%