NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1GX9J2VMTT8Q1EJJQPRH4Y
Run Details
Model:
Inception Mercury 2
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.3s
Cost:
$0.001830
Provider:
Inception
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9917%
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 night before the birthday bash, Molly paced the cramped attic, a flashlight flickering over a crumpled map of the suburban cul‑de‑sac. The garden was littered with balloons, a bouncy castle, and a table piled high with wrapped gifts. She could already hear the squeaky giggles of children, the clatter of plastic plates, and the distant hum of a pop‑song. Bill leaned against the broken window, his coat dusted with sawdust from the previous job. He checked his lock‑pick set, then tapped his foot, waiting for Molly’s signal. All they needed was timing, silence, and a sturdy bag for loot. "The gate is unlocked after the clown leaves at eight." "We’ll slip through the side gate, then hide behind the cake table." "I’ll disable the motion sensor with a magnet, you watch the kids." "If a parent spots us, we’ll duck behind the balloon arch." "The presents are in the big blue box, stacked near the punch." "Grab them fast, then slip out through the garden gate." "No noise? No lights, just the thrill of the haul." "And if the dog barks, we’ll toss a treat to distract it." "All set? Let’s move." "We’ll be legends after this."
created_at
"2026-03-06T12:10:43.145Z"
3/6/2026, 12:10:43 PM
model
"inception/mercury-2-20260304"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3228
moderation_latency
(null)
generation_time
3311
tokens_prompt
77
tokens_completion
1710
native_tokens_prompt
58
native_tokens_completion
2436
native_tokens_completion_images
(null)
native_tokens_reasoning
2181
native_tokens_cached
49
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
0.001830475
router
(null)
provider_responses
0
endpoint_id
"c2a24e34-c306-4b4d-9e2f-b162c2d8bf0e"
id
"chatcmpl-23bb9829-7119-4163-b668-85c4db051c87"
is_byok
false
latency
52
model_permaslug
"inception/mercury-2-20260304"
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-1772799043-CGLP7gVKztKKxRdRkxeV"
upstream_id
"chatcmpl-23bb9829-7119-4163-b668-85c4db051c87"
total_cost
0.001830475
cache_discount
0.000011025
upstream_inference_cost
0
provider_name
"Inception"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
198
100.00%
Dialogue to Total Word Ratio
Ratio: 49.49%, Deviation: 0.51%
neededClean
false
wordsTotal
198
wordsDialogue
98
99.9917%