NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBH2Y14S5W9623Z239AVBZ2
Run Details
Model:
Qwen 3.5 122B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 4s
Cost:
$0.031746
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
89.93%
Dialogue to Total Word Ratio
(details)
44.9641%
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
Molly adjusted her black mask. "The piƱata is definitely the structural weak point?" Bill checked his silver watch. "No, the clown. Clowns are inherently suspicious." "We need the Legos. Specifically the red ones." "Why red?" "High resale value on the dark web, Bill." "What about the cake?" "Distraction." "I love cake." "Focus on the objective." "Okay, okay. So we go in as waiters?" "No, we go in as the entertainment." "I can't sing." "Nobody asked you to sing. Just juggle." "I can't juggle." "Then don't drop the torches." "What torches?" "Improvisation." "This plan is absolute garbage." "It's foolproof." "Fools are everywhere." "Exactly. Now grab the balaclava." "It's itchy." "Do you want the toys or not?" "Fine. But if a kid cries, I'm out." "No crying. Only stealing." "Deal." "Wait, what about the parents?" "They are watching the clown." "And if they look?" "Then you juggle faster." "This is the worst idea." "It's the only idea." "Fine." "Let's move." "What about the security system?" "It's a cardboard box." "Are you sure?" "Positive." "Okay." "Good." "Let's go." "Wait, I forgot my gloves." "Leave them." "But the latex." "Forget the latex." "Okay." "What about the balloons?" "Pop them." "Why?" "Noise cover." "Smart." "I know." "Let's do this." "Wait, one more thing." "What?" "The dog." "We forgot the dog." "He's asleep." "Good." "Let's go." "Did you pack the bag?" "Yes." "Check it." "It's full." "Good." "Let's go."
created_at
"2026-02-25T23:10:30.441Z"
2/25/2026, 11:10:30 PM
model
"qwen/qwen3.5-122b-a10b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
455
moderation_latency
(null)
generation_time
63090
tokens_prompt
77
tokens_completion
8094
native_tokens_prompt
76
native_tokens_completion
9911
native_tokens_completion_images
(null)
native_tokens_reasoning
9489
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
0.0317456
router
(null)
provider_responses
0
endpoint_id
"33d466d1-d2f7-45ed-8ff3-fda7d2e32351"
id
"chatcmpl-8b65e936-ba8a-983a-9c0f-41fab120d804"
is_byok
false
latency
455
model_permaslug
"qwen/qwen3.5-122b-a10b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772061030-uAaY844SdFfLrd5TD9GC"
upstream_id
"chatcmpl-8b65e936-ba8a-983a-9c0f-41fab120d804"
total_cost
0.0317456
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
233
89.93%
Dialogue to Total Word Ratio
Ratio: 95.71%, Deviation: 5.71%
neededClean
false
wordsTotal
233
wordsDialogue
223
44.9641%