NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1HKX76M5V2YYPHN9NB6CXF
Run Details
Model:
Inception Mercury
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.4s
Cost:
$0.000194
Provider:
Inception
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
96.68%
Dialogue to Total Word Ratio
(details)
98.3009%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 moonlit backyard glowed with balloons and a faint scent of cake, while the party's laughter drifted across the fence. Molly: "So, Bill, we hit the house at midnight. The kids will be asleep, the presents will be in the living room." Bill: "Right, but we need a distraction. Maybe we can set off the sprinkler to make a splash and get the kids to the bathroom." Molly: "Good idea. I know a way to trigger it with a timer. Then we slip in through the back door." Bill: "And we need to avoid the security camera. I heard the vendor has a hidden sensor in the hallway." Molly: "I'll disable it with a small EMP chip. Then we can grab the gift boxes and stash them in the trash." Bill: "What about the cake? It's a big, sticky mess. We should leave it untouched to avoid suspicion." Molly: "Exactly. We'll just take the toys, the stuffed animals, and the party favors. No cake, no risk." Bill: "And after we exit, we should meet at the old warehouse. We'll split the loot and go our separate ways." Molly: "Deal. We'll be back before sunrise, and the police will never know we were there."
created_at
"2026-03-06T12:23:04.174Z"
3/6/2026, 12:23:04 PM
model
"inception/mercury"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2211
moderation_latency
(null)
generation_time
2365
tokens_prompt
77
tokens_completion
281
native_tokens_prompt
71
native_tokens_completion
254
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
63
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
0.000194075
router
(null)
provider_responses
0
endpoint_id
"da1082ea-721e-460e-b330-034ae7aefc7f"
id
"chatcmpl-90bb2370-e12d-48a8-8661-2c9e63101339"
is_byok
false
latency
52
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-1772799784-VT6yvfqk6AOlMkNa7h7U"
upstream_id
"chatcmpl-90bb2370-e12d-48a8-8661-2c9e63101339"
total_cost
0.000194075
cache_discount
0.000014175
upstream_inference_cost
0
provider_name
"Inception"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
203
96.68%
Dialogue to Total Word Ratio
Ratio: 85.71%, Deviation: 4.29%
neededClean
false
wordsTotal
203
wordsDialogue
174
98.3009%