NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCYN7GNSJM5NY2J7MWXTYE9
Run Details
Model:
Thinking Machines Inkling
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.9s
Cost:
$0.001345
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
67.7502%
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
"We're stealing every present?" "Every single one, Molly." "Even the bouncy castle?" "It's an inflatable, Bill." "Right, but is it wrapped?" "No one wraps air." "Good point. Pass the glitter." "Why do we need glitter?" "Distraction tactic." "We're breaking into a five-year-old's party." "Exactly. Chaos is already there." "You're right. What's our cover?" "We're balloon artists." "We don't know balloon animals." "Then we're very disappointing ones." "Brilliant. What's the exit strategy?" "We run with the loot bag while screaming 'It's not our fault!'" "That works for everything we've done." "True. Do we take the cake?" "Are you insane? Yes." "Chocolate or vanilla?" "Both. Always both." "Agreed. Tools?" "Duct tape, a duffel, and my dignity." "You lost that in 2019." "Rude but fair. Timing?" "When they sing happy birthday." "Perfect. Everyone's distracted." "Except the kid blowing candles." "He'll be too emotional to stop us." "Should we wear masks?" "Of course. Clowns." "Clowns? At a party?" "Who'd suspect clowns stealing gifts?" "Nobody expects a sad clown heist." "Exactly. Let's move." "Wait, what's the safe word?" "If anyone yells 'pinata,' we panic and scatter." "Done. Ready, partner?" "As ready as a clown with duct tape ever is."
created_at
"2026-07-25T15:35:17.791Z"
7/25/2026, 3:35:17 PM
model
"thinkingmachines/inkling-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
194
moderation_latency
(null)
generation_time
2433
tokens_prompt
75
tokens_completion
324
native_tokens_prompt
73
native_tokens_completion
314
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
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
0.0013447
router
(null)
provider_responses
0
endpoint_id
"9911deb9-f44e-4e18-87fe-9d7b60acee72"
id
"otYnP5R-6z2FuN-a20c3bd06963a22b"
is_byok
false
latency
194
model_permaslug
"thinkingmachines/inkling-20260715"
provider_name
"Together"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784993717-R0bEmmiKFQBUsi5TXwIt"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784993717-VmIyEYtxPvvzldsQI5OV"
upstream_id
"otYnP5R-6z2FuN-a20c3bd06963a22b"
total_cost
0.0013447
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
194
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
196
wordsDialogue
196
67.7502%