NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ7244XNTESFZJH2YE8JCR7B
Run Details
Model:
Qwen 3.6 27B
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
1m 39s
Cost:
$0.018565
Provider:
Morph
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.01%
Dialogue to Total Word Ratio
(details)
0.0027%
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 adjusted sunglasses, watching the spin cycle. Bill sat on a dryer, peeling a juice sticker. "The trajectory is suboptimal," Molly muttered, tapping a scribbled napkin. "Forty-two minutes until the piñata. We need a distraction louder than a screaming toddler." Bill slurped. "Aiming for presents, Mo. Silencing the toddler feels like a union violation." Molly smoothed the napkin. "Toddler is the siren. Presents are the gold. Parents are trading gluten-free brownies. Attention spans short. We exploit that." Bill glanced up. "Gluten-free? Health-conscious mark? My stealth is calibrated for chaos, not kale." Molly pointed. "Sixth birthday. Chaos inherent. Mom is a yoga instructor using passive-aggressive breathing for communication. When she holds downward-dog, we slide through the pet door." Bill laughed. "Pet door? I have substantial girth and moral ambiguity. I kick doors open with style." Molly scribbled. "Not if you want the Lego space station. Wrapped in cartoon cat paper. Beneath the tree. Mine." Bill lowered the pouch. "The space station exists?" Bill paled. "I would kill for it. Pet door. Fine. But I'm wearing the thermal compression suit." "July? Party smells like latex and sugar?" Molly asked. "Aerodynamic. Plus, if caught, I look like an inflatable tube man. Buys twelve seconds. Eternity for holding Legos." Molly scribbled. "Fine. Tube man decoy. I take the window. Posing as late DJ. Mixer in tote bag." Bill patted pockets. "My role? Aggressive breakdancing distraction?" "Cut the rope. Drop the piñata. Donkey falls. Children descend. I grab bags." "Drop the donkey? Malicious." "Efficient. Plastic donkey is irrelevant. Father is the threat. Former competitive eater eyeing cookie table with predatory focus. Sees us, tackles us, eats shoes." Bill paled. "Eaten shoes? Violation of Geneva Convention of Thieves." "Drop donkey swiftly. On my mark. Wire cutters ready?" "Ready. Keep the cupcakes?" "Only if not evidence. Check watch. Balloon guy is setting up. Giraffe before we move means failure." Bill stood. "After you. Avoid glitter. It gets in socks." "Just presents, Bill. Childhood stays with victim. We are professionals."
created_at
"2026-04-27T08:50:33.019Z"
4/27/2026, 8:50:33 AM
model
"qwen/qwen3.6-27b-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
824
moderation_latency
(null)
generation_time
99319
tokens_prompt
77
tokens_completion
7285
native_tokens_prompt
76
native_tokens_completion
7718
native_tokens_completion_images
(null)
native_tokens_reasoning
6703
native_tokens_cached
64
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"
usage
0.018565
router
(null)
provider_responses
0
endpoint_id
"826cab4e-dc26-4472-83be-e4ddd5ebd2ab"
id
"c98e4d14e754439cb9604cf06b66d2be"
is_byok
false
latency
660
model_permaslug
"qwen/qwen3.6-27b-20260422"
provider_name
"Morph"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777279833-nnzU3LNrEcZk4G9qgiGD"
session_id
(null)
api_type
"completions"
id
"gen-1777279833-FDi7HpwDQGm3qUmQRhXs"
upstream_id
"c98e4d14e754439cb9604cf06b66d2be"
total_cost
0.018565
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Morph"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
332
0.01%
Dialogue to Total Word Ratio
Ratio: 84.02%, Deviation: 14.02%
neededClean
false
wordsTotal
338
wordsDialogue
284
0.0027%