NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ73T7FVCM02H503SZEGJEP9
Run Details
Model:
Qwen 3.6 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 48s
Cost:
$0.035951
Provider:
Morph
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
50.0000%
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
Molly crept behind the bouncy castle. Bill adjusted his party hat. "The ventilation grate sits right above the cake table. "Excellent. I have the crowbar and my trusty party streamer. "Streamers cannot cut drywall, darling. Use the glitter glue dispenser. It remains sticky enough to climb the wall. "Noted. I will swap the adhesive for a plasma cutter. Wait, can we simply wait until the children open them? "We never wait, we strike early. Speed defines us. I will distract the parents with a rehearsed magic trick. "You cannot even make a coin vanish. "I make their focus vanish. Same concept. Then we drop in, grab every box under three feet, and vanish. "What signals the drop? "I blow the party whistle. Twice. If I blow it three times, run and pretend to be a confused clown. "And if a kid offers us cake? "Ignore it. We are professionals. We never eat cake. Though if the box says dinosaur, I claim first dibs. "You promised it was yours. "Flexibility wins jobs. Check your grappling hook. "It remains a yo-yo. "Modify it fast. Wrap the string around the chandelier and swing down like a deranged guest. "Shall we practice? "Practice what?
created_at
"2026-04-27T09:20:05.12Z"
4/27/2026, 9:20:05 AM
model
"qwen/qwen3.6-27b-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
685
moderation_latency
(null)
generation_time
167836
tokens_prompt
77
tokens_completion
10653
native_tokens_prompt
76
native_tokens_completion
14962
native_tokens_completion_images
(null)
native_tokens_reasoning
10366
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
0.0359506
router
(null)
provider_responses
0
endpoint_id
"826cab4e-dc26-4472-83be-e4ddd5ebd2ab"
id
"f0c6aa3d7a674d9ebaf1d262b5c003c5"
is_byok
false
latency
664
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-1777281605-n9guuFlijAlcHyWYyGIP"
session_id
(null)
api_type
"completions"
id
"gen-1777281605-PUUqyGoAUdWtTFeRYxhK"
upstream_id
"f0c6aa3d7a674d9ebaf1d262b5c003c5"
total_cost
0.0359506
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Morph"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
0.00%
Dialogue to Total Word Ratio
Ratio: 68.16%, Deviation: 21.84%
neededClean
false
wordsTotal
201
wordsDialogue
137
50.0000%