NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ6ZW5VC7JMQSX6HVY06FMVT
Run Details
Model:
Qwen 3.5 Plus (2026-04-20)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2m 1s
Cost:
$0.019283
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
99.93%
Dialogue to Total Word Ratio
(details)
99.6544%
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
Bill smoothed the crayon map against his knee, the parchment smelling of goldfish crackers and professional failure, while Molly adjusted her tactical tiara, a crown duct-taped to swimming goggles that fogged with nervous breath. The blueprints were less a strategic guide and more a glitter-bombed napkin sketch scribbled in purple marker, yet Bill insisted the stick figure labeled 'Wolf' marked the loot. Molly pointed her cat-toy laser at the neon bouncy castle, a pulsating fortress of pink and blue foam awaiting their dignity in a single bound. She checked her satchel of bubble solution, ready to blind the tiny hostiles armed with sticky fingers and unbridled enthusiasm. Bill tapped his wristwatch, covered by a taco sticker, and hissed, "The juice boxes are open. The guards are wet and wiggly. On my mark." "Check the slide," Molly hissed back. She cracked her knuckles inside plush paw mittens, stared at the chaos of sugar rushes, and prepared to secure thirty crates of stolen joy. "Move," she whispered. Bill nodded, and they advanced toward the slide, weapons of mass distraction primed for the greatest heist in nursery rhyme history, praying the piƱata would hold out. "Go," Bill breathed.
created_at
"2026-04-27T08:11:14.676Z"
4/27/2026, 8:11:14 AM
model
"qwen/qwen3.5-plus-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
700
moderation_latency
(null)
generation_time
121004
tokens_prompt
77
tokens_completion
7328
native_tokens_prompt
76
native_tokens_completion
8022
native_tokens_completion_images
(null)
native_tokens_reasoning
7754
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
0.0192832
router
(null)
provider_responses
0
endpoint_id
"8b4a0fbb-6705-4f8d-a7f1-ad18ecc0edbc"
id
"chatcmpl-2efa2ba5-e50a-957a-81f0-8df0c1d656b5"
is_byok
false
latency
700
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-1777277474-p0shafnKV28inCMR01oL"
session_id
(null)
api_type
"completions"
id
"gen-1777277474-yrvqvBflpDX1uvcCmMM3"
upstream_id
"chatcmpl-2efa2ba5-e50a-957a-81f0-8df0c1d656b5"
total_cost
0.0192832
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
195
99.93%
Dialogue to Total Word Ratio
Ratio: 11.62%, Deviation: 1.62%
neededClean
false
wordsTotal
198
wordsDialogue
23
99.6544%