NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1H91J57VT7MEARPPCY3KN2
Run Details
Model:
Inception Mercury
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
12.2s
Cost:
$0.000227
Provider:
Inception
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
99.80%
Dialogue to Total Word Ratio
(details)
87.4783%
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
On a rainy Saturday, the city's bright neon glow flickered over the rooftop where the thieves gathered. The air smelled of wet pavement and distant fireworks. Molly adjusted her black hoodie, while Bill checked the map of the venue, noting the kids’ party at the old community center. They had rehearsed the plan for weeks, each detail refined to avoid security cameras. The party would be a distraction, with balloons, music, and endless candy. Their goal was simple: slip through the back entrance, locate the gift table, and exit with the loot before the parents returned. The clock ticked, and the night grew thicker. Molly: "We need to hit party when kids are distracted by big clown and the laughter and the kids' giggles. I’ll slip through side door while you keep an eye on parents." Bill: "Got it. I’ll use map to find big gift table, we’ll grab presents and vanish before anyone notices." Molly: "Remember security cameras. I’ve plotted blind spot near hallway. You’ll need to disable the alarm with the gadget I stole from the tech shop." Bill: "And candy? I’ll use it as distraction and the candy will be used." Molly: "Perfect. Let’s synchronize. I’ll start at 9:15, you at 9:20. We’ll be in and out before party ends."
created_at
"2026-03-06T12:17:08.174Z"
3/6/2026, 12:17:08 PM
model
"inception/mercury"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
11920
moderation_latency
(null)
generation_time
12170
tokens_prompt
77
tokens_completion
327
native_tokens_prompt
73
native_tokens_completion
283
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
17
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
0.000226675
router
(null)
provider_responses
0
endpoint_id
"da1082ea-721e-460e-b330-034ae7aefc7f"
id
"chatcmpl-93c7cf89-993a-4391-a770-7d025d259a30"
is_byok
false
latency
43
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-1772799428-b7hZZFv9dd4yTC8tVasA"
upstream_id
"chatcmpl-93c7cf89-993a-4391-a770-7d025d259a30"
total_cost
0.000226675
cache_discount
0.000003825
upstream_inference_cost
0
provider_name
"Inception"
Evaluation details
Result
Evaluator
Details
Meta Data
75.16%
Matches word count
n/a
neededClean
false
words
213
99.80%
Dialogue to Total Word Ratio
Ratio: 52.11%, Deviation: 2.11%
neededClean
false
wordsTotal
213
wordsDialogue
111
87.4783%