NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1J1J29M347889J0E708XX2
Run Details
Model:
Inception Mercury 2
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
15.1s
Cost:
$0.009410
Provider:
Inception
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.55%
Dialogue to Total Word Ratio
(details)
99.7741%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 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 old warehouse on Maple Street had been empty for years, its windows boarded and its walls whispering of forgotten parties. Tonight, Molly and Bill stood in the dim light, backpacks slung over their shoulders. The kids’ birthday bash was next door, music thumping through thin walls. They had scoped the place earlier, noting the back entrance, the flickering hallway bulb, and the unattended security camera. Their plan was simple: slip in, grab the gifts, and disappear before the cake was cut. Molly: "Do you think the kids will notice if we walk out with every present, or will the clown keep them busy?" Bill: "Most gifts will be hidden under balloons; only a missing superhero cape might raise eyebrows." Molly: "Timmy’s name is on the biggest box, and he loves capes and dinosaur socks." Bill: "The parents will be busy with the magician, so a missing cape won’t matter." Molly: "What about the security camera above the snack table?" Bill: "I jammed it with a portable device; it’s just a dead eye now." Molly: "The alarm on the front door is set to silent, right?" Bill: "Exactly, it only blares if someone forces the lock." Molly: "We go in at 7:45, just before the piñata is smashed." Bill: "Perfect timing; the kids will be shouting ‘Happy Birthday’ and chasing candy." Molly: "I’ll take the top shelf, you grab the lower crates with plush toys." Bill: "After we’re out, we head to the van and disappear before the cake is cut." Molly: "If we get caught, I’ll claim the cat knocked over a vase, and we’ll both be cleared." Bill: "The cat is our perfect alibi; nobody suspects a feline in a heist." Molly: "Let’s move fast; the cake will be cut in two minutes, and the clown will start the dance." Bill: "All right, on three—one, two, three—let's grab everything and vanish." Molly: "We’ll split the loot later, and I’ll buy a new pair of shoes with the extra socks." The clock on the wall ticked louder than the distant giggles drifting from the party next door. Molly slipped the lock pick into the back door, feeling the familiar click as the bolt retracted. Bill slipped a sack into his jacket, the fabric already bulging with anticipation. They moved like shadows, their footsteps muffled by the thick carpet. The hallway was lined with colorful streamers, a stark contrast to the warehouse’s gloom. A faint scent of frosting seeped through the cracked wall, making Molly’s stomach rumble. The two thieves slipped through the back door just as the first slice of cake was lifted onto a plate. The van waited a few blocks away, a silent accomplice. They piled the loot inside: bright parcels, plush animals, and a handful of cartoon dinosaur socks. As they drove off, the children’s laughter faded, replaced by the engine’s low hum. Molly grinned, whispering, “We did it,” while Bill stared ahead, already dreaming of Bali’s beach and their next big score.
created_at
"2026-03-06T12:30:31.506Z"
3/6/2026, 12:30:31 PM
model
"inception/mercury-2-20260304"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
14683
moderation_latency
(null)
generation_time
15068
tokens_prompt
77
tokens_completion
6417
native_tokens_prompt
58
native_tokens_completion
12529
native_tokens_completion_images
(null)
native_tokens_reasoning
11871
native_tokens_cached
4
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
0.00941035
router
(null)
provider_responses
0
endpoint_id
"c2a24e34-c306-4b4d-9e2f-b162c2d8bf0e"
id
"chatcmpl-2fa50374-5bbd-45cd-bd78-1f34f0ceabe9"
is_byok
false
latency
51
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-1772800231-EnKA7OsmhLfzJBubW6GW"
upstream_id
"chatcmpl-2fa50374-5bbd-45cd-bd78-1f34f0ceabe9"
total_cost
0.00941035
cache_discount
9e-7
upstream_inference_cost
0
provider_name
"Inception"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
499
99.55%
Dialogue to Total Word Ratio
Ratio: 49.70%, Deviation: 0.30%
neededClean
false
wordsTotal
499
wordsDialogue
248
99.7741%