NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBKEJYX2APMR3EJ7SYVTFQ6
Run Details
Model:
Qwen 3.5 122B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 6s
Cost:
$0.023502
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
51.66%
Dialogue to Total Word Ratio
(details)
75.8312%
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
"Are you sure about the cake?" Molly asked. "It's frosting, Bill. Frosting is a distraction." "But the piñata. It's full of candy." "We're here for the unwrapped gifts, not sugar." "What if the parents catch us?" "They'll be too busy fighting over who brought the best dip." "Okay, but the clown." "The clown is a liability. We neutralize the clown immediately." "Neutralize? You mean hide him?" "Put him in the closet. Lock him with the balloons." "That feels illegal." "Stealing presents from six-year-olds feels incredibly illegal too." "I mean, technically." "Technically, we're redistributing wealth to the deserving." "To us." "Exactly. Now, grab the black hoodies." "Do we have black hoodies?" "Yes, but they're neon green and shiny." "Perfect camouflage for a birthday party." "Bill, stop." "I'm just saying, green is festive." "We leave in exactly five minutes." "What about the loot?" "Split it. Half and half, no exceptions." "Unless you want the PS5." "I want the PS5 and the games." "Then you carry the heavy boxes yourself." "Deal." "Wait, is that a balloon animal?" "Drop it, Bill." "It looks like a dog." "It's a dog." "I'm keeping it." "Leave the dog." "Fine." "Let's go." "And the piñata?" "We smash it." "Perfect."
created_at
"2026-02-25T23:51:49.473Z"
2/25/2026, 11:51:49 PM
model
"qwen/qwen3.5-122b-a10b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
503
moderation_latency
(null)
generation_time
66390
tokens_prompt
77
tokens_completion
5401
native_tokens_prompt
76
native_tokens_completion
7335
native_tokens_completion_images
(null)
native_tokens_reasoning
6986
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0235024
router
(null)
provider_responses
0
endpoint_id
"33d466d1-d2f7-45ed-8ff3-fda7d2e32351"
id
"chatcmpl-370bc240-909d-9381-85b3-e9b248e2a1d9"
is_byok
false
latency
503
model_permaslug
"qwen/qwen3.5-122b-a10b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772063509-tYxHXQuADmhU0JoxAjef"
upstream_id
"chatcmpl-370bc240-909d-9381-85b3-e9b248e2a1d9"
total_cost
0.0235024
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
201
51.66%
Dialogue to Total Word Ratio
Ratio: 99.01%, Deviation: 9.01%
neededClean
false
wordsTotal
203
wordsDialogue
201
75.8312%