NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBDP6EQJGMG6N7NRWY4GGNT
Run Details
Model:
Qwen 3.5 122B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 25s
Cost:
$0.040808
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
27.17%
Matches word count
(details)
99.93%
Dialogue to Total Word Ratio
(details)
63.5503%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 tactical mask, peering through the frosted glass of the suburban window. The muffled sounds of Happy Birthday drifted through the pane like a siren song calling to the wicked. They crouched low behind the hydrangeas, hidden by the shadows of the ancient oak tree. They crept forward across the green manicured lawn slowly. Bill checked his watch. Molly nodded solemnly at him. Molly sighed heavily with frustration. They vanished into the dark cold night. "The cake is the distraction," she whispered, checking her leather gloves. "Too risky for us." "He’s a clown, Bill. He knows balloons and face paint." "What about the piñata?" Bill asked, adjusting his heavy backpack straps. "That’s the vault. Full of candy and loose change." "And what about the big Lego?" "Secondary target. High resale value on the black market." Molly nodded solemnly. "Ready?" "Born ready." "Wait," Bill said suddenly, freezing in place. "The dog." "A corgi?" "A corgi. It’s a guard dog right?" "It’s a potato with legs really." "Exactly. Highly dangerous indeed." Molly sighed heavily. "Fine. We wait for the parents to leave now." "Or we distract it with a sausage link." "Genius plan." "One last thing," Bill said quietly. "What do you mean?" "Do we leave a note here?" "No, absolutely never, Bill." "Cool, works for me perfectly."
created_at
"2026-02-25T22:11:07.356Z"
2/25/2026, 10:11:07 PM
model
"qwen/qwen3.5-122b-a10b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
487
moderation_latency
(null)
generation_time
85093
tokens_prompt
77
tokens_completion
11337
native_tokens_prompt
76
native_tokens_completion
12743
native_tokens_completion_images
(null)
native_tokens_reasoning
12408
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
0.040808
router
(null)
provider_responses
0
endpoint_id
"33d466d1-d2f7-45ed-8ff3-fda7d2e32351"
id
"chatcmpl-b533b631-69e1-9113-a374-570592828987"
is_byok
false
latency
487
model_permaslug
"qwen/qwen3.5-122b-a10b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772057467-UkrIvA72G9xlTF0g2GyI"
upstream_id
"chatcmpl-b533b631-69e1-9113-a374-570592828987"
total_cost
0.040808
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
27.17%
Matches word count
n/a
neededClean
false
words
219
99.93%
Dialogue to Total Word Ratio
Ratio: 51.60%, Deviation: 1.60%
neededClean
false
wordsTotal
219
wordsDialogue
113
63.5503%