NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBGVR82P68962Q9N9BJEJRG
Run Details
Model:
Qwen 3.5 35B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 6s
Cost:
$0.020005
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.2661%
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
Molly adjusted the thermal scope on her rifle while Bill checked the perimeter with a pair of binoculars that smelled faintly of old cheese. They were perched on the edge of the roof overlooking the suburban backyard, where a lopsided castle balloon deflated under the weight of its own hubris. Fireworks would soon distract the parents, allowing them to slide down the gutter unnoticed. The plan was simple, reckless, and financially viable. Molly wiped sweat from her forehead and scanned the glowing window where the unwrapped plastic wrapped toys sat in a mountain of silence. She turned to her partner. She whispered. He nodded. She checked her grappling hook. Bill adjusted his camouflage poncho. The party was just starting. They waited for the cake cutting. Bill looked at her. Molly looked back. The tension was palpable. A neighbor was eating a hot dog. It was perfect timing. Bill said, Are you ready for the drop now. Molly replied, I am definitely ready. Bill nodded again. Molly said, Let’s go steal all of them now. Bill whispered, Okay then. Molly sighed. They began the descent. They landed softly on the carpet inside. The presents were there. They started filling bags. They heard someone yell stop.
created_at
"2026-02-25T23:06:35.145Z"
2/25/2026, 11:06:35 PM
model
"qwen/qwen3.5-35b-a3b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
492
moderation_latency
(null)
generation_time
66132
tokens_prompt
77
tokens_completion
7974
native_tokens_prompt
76
native_tokens_completion
9993
native_tokens_completion_images
(null)
native_tokens_reasoning
9733
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
0.020005
router
(null)
provider_responses
0
endpoint_id
"48c1210f-b7d2-4688-a340-f7424fc99d2b"
id
"chatcmpl-1e8ed7f7-fc8e-9d9e-8e87-b1cbecd07928"
is_byok
false
latency
492
model_permaslug
"qwen/qwen3.5-35b-a3b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772060795-Xpl2uVw781EqFhku0RAw"
upstream_id
"chatcmpl-1e8ed7f7-fc8e-9d9e-8e87-b1cbecd07928"
total_cost
0.020005
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
36.79%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 10.00%
neededClean
false
wordsTotal
204
wordsDialogue
0
68.2661%