NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ6Z6PXQC69ZBKVEC1ETVPZV
Run Details
Model:
Qwen 3.5 Plus (2026-04-20)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3m
Cost:
$0.028775
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
99.47%
Dialogue to Total Word Ratio
(details)
87.3134%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 her tactical earpiece, which was actually a stuffed giraffe head glued to a Walkman. Bill was busy duct-taping a bouncy castle to a dolly. The target sat across the street, a suburban fortress of streamers and chaos. A clown wept in the corner of the yard. "The cake is the real prize. I love chocolate," Molly whispered. "But today, we focus on loot. Also, grab the big glitter cannon." Bill wiped grease on his overalls, revealing a "My First Heist" apron underneath. They had studied the patterns. The parents would be distracted by a piƱata distraction deployed via drone. The toddlers would be pacified with sticky juice boxes laced with mild sedatives. The presents, wrapped in glittering paper that snagged on everything, were stacked like a tactical fortress near the buffet. Molly checked her checklist. Grapple hook disguised as a jump rope. Bill signaled the all-clear by honking a rubber chicken. The clock struck three. It was nap time for the weak, but heist time for the wicked. They moved, silhouettes against the balloons, ready to reap the whirlwind of bubble wrap and plastic frustration.
created_at
"2026-04-27T07:59:31.261Z"
4/27/2026, 7:59:31 AM
model
"qwen/qwen3.5-plus-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
698
moderation_latency
(null)
generation_time
180320
tokens_prompt
77
tokens_completion
9155
native_tokens_prompt
76
native_tokens_completion
11977
native_tokens_completion_images
(null)
native_tokens_reasoning
11724
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
0.0287752
router
(null)
provider_responses
0
endpoint_id
"8b4a0fbb-6705-4f8d-a7f1-ad18ecc0edbc"
id
"chatcmpl-e6d9102e-e4cd-91ed-ad31-8750bdda9caa"
is_byok
false
latency
698
model_permaslug
"qwen/qwen3.5-plus-20260420"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777276771-it6vUGgEnrAqQSVTxKyP"
session_id
(null)
api_type
"completions"
id
"gen-1777276771-uymILQvNhOZQKK987WoV"
upstream_id
"chatcmpl-e6d9102e-e4cd-91ed-ad31-8750bdda9caa"
total_cost
0.0287752
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
75.16%
Matches word count
n/a
neededClean
false
words
187
99.47%
Dialogue to Total Word Ratio
Ratio: 12.70%, Deviation: 2.70%
neededClean
false
wordsTotal
189
wordsDialogue
24
87.3134%