NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ726XJ8WY64ZPKNTXCPB47K
Run Details
Model:
Qwen 3.6 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2m 12s
Cost:
$0.031488
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
91.26%
Dialogue to Total Word Ratio
(details)
95.6198%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
The sprinklers hissed against the manicured lawn as Molly adjusted her velvet mask, which frankly did nothing to conceal her face but felt terribly authentic. Bill squatted behind a prize-winning hydrangea, polishing a pair of industrial tin snips with a frayed bandana. Inside, the shrieks of overcaffeinated preschoolers echoed through the open patio doors like a distant warning siren. "This is it," Bill whispered, breath fogging the chill. "The ultimate score. Do you realize what loot a tenth birthday generates? Action figures, glitter paste, and enough plastic swords to arm a militia." Molly checked her watch. "I realize we are stealing a ride-on lawnmower and educational blocks. Focus. The father leaves at eight. We slip past the piƱata guard and load the duffels before cake time." "Understood," Bill snapped the snips shut. "Operation Confetti is go. I packed the bungee cords. Do we split the loot or roll it into one massive pile?" He stood, brushing dirt from his stained khakis, completely ignoring the jingle of his belt. Molly tightened her grip on the canvas bag and nodded toward the trellis. Neon balloons bobbed near the gutter. They waited. "Less chatter, more climbing. We move in thirty seconds."
created_at
"2026-04-27T08:52:03.791Z"
4/27/2026, 8:52:03 AM
model
"qwen/qwen3.6-27b-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
832
moderation_latency
(null)
generation_time
131529
tokens_prompt
77
tokens_completion
7402
native_tokens_prompt
76
native_tokens_completion
8734
native_tokens_completion_images
(null)
native_tokens_reasoning
8459
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
0.031488
router
(null)
provider_responses
0
endpoint_id
"82097366-3a73-4790-ac36-f96ba9f6f577"
id
"chatcmpl-dc7e549d-d2fb-95d7-a37b-d61bd1762259"
is_byok
false
latency
832
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-1777279923-HRWvFNxob7BbII0lGaoL"
session_id
(null)
api_type
"completions"
id
"gen-1777279923-KV8xbxtBur20NK27RfLV"
upstream_id
"chatcmpl-dc7e549d-d2fb-95d7-a37b-d61bd1762259"
total_cost
0.031488
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
198
91.26%
Dialogue to Total Word Ratio
Ratio: 44.50%, Deviation: 5.50%
neededClean
false
wordsTotal
200
wordsDialogue
89
95.6198%