NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ72H5WPRRRJ0S9040C602R0
Run Details
Model:
Qwen 3.6 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 42s
Cost:
$0.025472
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
64.84%
Dialogue to Total Word Ratio
(details)
82.1074%
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
"So, the target's the Mayor's kid's birthday bash?" Molly asked. "Affirmative," Bill hissed. "Cake, and six hundred dollars in LEGO sets unboxed by an impatient six-year-old." "Why presents? Don't we hit buffets for silverware?" "Silverware triggers alarms. Toys trigger indifference. It's gravity-based theft. Plus, the dad collects rare action figures." "What's the breach?" "The piƱata. We hollow the donkey, insert ourselves, and wait for blindfolded brats to swing. We absorb impact, roll out the back, and scatter." "Lawsuit territory. I prefer less bruising." "Option two: Bouncy Castle Infiltration. Crawl the blower duct, drop into the ball pit, pose as malfunctioning animatronics." "Animatronics?" "Chaos creates cover. While adults investigate twitching clown suits, we vacuum the gift table with this shop-vac." "What about the juice box zone?" "Deadly. Sticky floors slow us down. We route past the snack table, grab cupcakes for weight distribution, and dump them on the path." "You brought the shop-vac?" "I bring everything. Operation Unwrapping is a go, right?" "Only if no glitter tutus." "Negotiable. Just grab the tape." "Wait, what about the balloon arch?" "Absolute trap. Pop it and the dad drops a net. Ex-military. Stick to the plan." "Fine. If sprinkles hit me, you're buying smoothies." "Deal. Just kiss the shop-vac."
created_at
"2026-04-27T08:57:40.002Z"
4/27/2026, 8:57:40 AM
model
"qwen/qwen3.6-27b-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
731
moderation_latency
(null)
generation_time
101152
tokens_prompt
77
tokens_completion
6862
native_tokens_prompt
76
native_tokens_completion
7063
native_tokens_completion_images
(null)
native_tokens_reasoning
6710
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"
usage
0.0254724
router
(null)
provider_responses
0
endpoint_id
"82097366-3a73-4790-ac36-f96ba9f6f577"
id
"chatcmpl-8cdd65a2-2862-98d1-bbc0-1739771f7f2e"
is_byok
false
latency
731
model_permaslug
"qwen/qwen3.6-27b-20260422"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777280260-uPKEVbKuaHdpdubTkJwT"
session_id
(null)
api_type
"completions"
id
"gen-1777280260-wJHVonYmErQ0jb0WRFPP"
upstream_id
"chatcmpl-8cdd65a2-2862-98d1-bbc0-1739771f7f2e"
total_cost
0.0254724
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
205
64.84%
Dialogue to Total Word Ratio
Ratio: 98.11%, Deviation: 8.11%
neededClean
false
wordsTotal
212
wordsDialogue
208
82.1074%