NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ70MEKWZM6X457VB8VNG031
Run Details
Model:
Qwen 3.5 Plus (2026-04-20)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 5s
Cost:
$0.010386
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
97.85%
Dialogue to Total Word Ratio
(details)
92.1160%
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 plan is simple," Molly whispered, adjusting her earwig. "We hit the backyard, grab the loot, and vanish." "Vanish into a bouncy castle?" Bill asked, checking his grappling hook. "Molly, there are minors. Toddlers, Molly. They have sticky hands. I can't lose a finger to a juice box." "It's the Christmas party, Bill! The presents tower is massive! I saw the list. Legos, tablets, a pony!" "A pony? You want to heist a pony?" "I want to fence a pony!" "The security is a golden retriever named Waffles." "Exactly! He's got a treat distribution schedule. If we bring better treats, he's ours." "I brought steak jerky." "Good man. Now, the entry. Climb the trellis?" "Trellis is unstable. We go through the clown car." "There's a clown car?" "For hire. The clown is currently drunk in the toilet. We hide inside." "Bill, that's brilliant and disturbing. You're hired." "Does the pony come with a saddle?" "Focus, Bill. Presents only. No snacking." "Wait, if we take the pony, how do we transport it?" Bill hissed. "We put it in the clown car." "That's not a thing, Molly! Physics doesn't work that way!" "Everything is a thing with enough duct tape and desperation. Now quit complaining and polish the earwig. Ride at four."
created_at
"2026-04-27T08:24:30.083Z"
4/27/2026, 8:24:30 AM
model
"qwen/qwen3.5-plus-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
646
moderation_latency
(null)
generation_time
65327
tokens_prompt
77
tokens_completion
3899
native_tokens_prompt
76
native_tokens_completion
4315
native_tokens_completion_images
(null)
native_tokens_reasoning
3983
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
0.0103864
router
(null)
provider_responses
0
endpoint_id
"8b4a0fbb-6705-4f8d-a7f1-ad18ecc0edbc"
id
"chatcmpl-520c8282-915c-9742-a096-e74ffa295750"
is_byok
false
latency
646
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-1777278270-rb2ysTnJH14h9GGMPfjR"
session_id
(null)
api_type
"completions"
id
"gen-1777278270-QQ65vSZvwlxpc2jVdrj6"
upstream_id
"chatcmpl-520c8282-915c-9742-a096-e74ffa295750"
total_cost
0.0103864
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
211
97.85%
Dialogue to Total Word Ratio
Ratio: 93.84%, Deviation: 3.84%
neededClean
false
wordsTotal
211
wordsDialogue
198
92.1160%