NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCW5FVCETYBSPDNSE9M8NSQ
Run Details
Model:
Thinking Machines Inkling (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
3m 14s
Cost:
$0.006771
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0014%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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
Molly slid the crumpled blueprint across the sticky diner table. "Look at this, Bill. Pineview Community Center. Twin birthday bash for some tech-bro's kids. Starts at two, ends at four, and every present is stacked on a table right beside the service entrance." Bill poked the paper with a greasy fry. "That red circle? That's the table? It looks like a throne made of LEGO and regret." "It's not a throne. It's an opportunity." Molly sipped her coffee, black and bitter. "You're in, right?" Bill chewed slowly. "How many toddlers?" "Forty. Maybe fifty. The invitation said all friends welcome, and in that zip code that means every child with a nanny and a trust fund." Bill winced. "Forty screaming sugar bombs? That's not a heist, Molly. That's a war crime against my nerves." "It's cover," Molly said. "The parents are distracted by artisanal juice boxes. The magician is probably high on his own smoke. The back door has a broken latch I already tested." "You tested it?" "Yesterday. Dressed as a plumber. Nobody questioned a woman with a wrench and unshakable confidence." Molly leaned closer. "We go in at two-fifteen, when the puppet show peaks. We exit by two-forty, before they cut the cake. The present table is loaded with electronics disguised as toys. One box has a drone. Another has noise-canceling headphones for a six-year-old. This isn't about teddy bears, Bill. It's about luxury goods intercepting sticky hands." Bill rubbed his temples. "My mother always said I'd end up in prison or politics. She never mentioned robbing a bouncy castle." "We aren't robbing the castle. We're robbing the table behind it." Molly pulled out a list. "You wear the rented bear costume. I'm your handler." "I'm allergic to polyester." "Then sneeze quietly." She tapped the paper. "The bear is your cover. Kids will hug you. Use the hug to hide the bag. I've seen you embrace worse situations for far less money." "They'll hug me?" "Yes. Embrace it. You're a bear, Bill. You are literally huggable criminal infrastructure." Bill sighed. "What's the split?" "Sixty-forty. I'm the planner." "I'm the furry mule!" "Exactly. Premium labor requires premium pay, which in this case is forty percent of stolen drones." Molly folded the map. "We meet at the van at one-forty-five. Don't be late. And Bill?" "Yeah?" "Don't eat the cupcakes. They're gluten-free and taste like moral failure." Bill stood, scraping his chair against the floor. "This is absolutely the lowest I've ever sunk." Molly grinned, sliding the paper into her jacket. "The floor's made of gold, Bill. Now go try on the paws. We have presents to liberate before nap time ends."
created_at
"2026-07-25T14:51:44.888Z"
7/25/2026, 2:51:44 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
933
moderation_latency
(null)
generation_time
194285
tokens_prompt
75
tokens_completion
1810
native_tokens_prompt
75
native_tokens_completion
1660
native_tokens_completion_images
(null)
native_tokens_reasoning
1133
native_tokens_cached
32
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
service_tier
(null)
usage
0.00677144
router
(null)
provider_responses
0
endpoint_id
"d6b9d68e-115a-49d7-81cd-1ad1c6942b0e"
id
"chatcmpl-RVMKudcMXY9LtLw0GE53k5ru"
is_byok
false
latency
115
model_permaslug
"thinkingmachines/inkling-20260715"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784991104-cXkXHgWsfdsXI3dVh64I"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784991104-cr4Hc3ggWn4KPkFRxXBF"
upstream_id
"chatcmpl-RVMKudcMXY9LtLw0GE53k5ru"
total_cost
0.00677144
cache_discount
0.00002656
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
441
0.00%
Dialogue to Total Word Ratio
Ratio: 84.48%, Deviation: 14.48%
neededClean
false
wordsTotal
451
wordsDialogue
381
0.0014%