NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBJRFX21VTQ4RYTQ3BJ3KX1
Run Details
Model:
Qwen 3.5 35B
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
37.6s
Cost:
$0.010859
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 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 crouched behind the hydrangeas, adjusting her night vision goggles. Focus, Bill. The security system is the only thing we cannot hack. You need to stay calm. Bill shivered in the cold grass. It is a toy store, Molly. Not a bank. Why are we breaking into a birthday party for a five year old? The parents bought the entire inventory. Look at the wrapping paper. That is vintage. We can fence it for a fortune. It says Happy Birthday on it. They will notice if it is gone. Not if we replace it with rocks. We learned that from the bank job in Jersey. That went badly. Three days in the can. We had no choice. The guard was wearing a tuxedo. Intimidation is key. The cake is coming out in ten minutes. That is our window. Ten minutes? I have to hide? No, you have to be the clown. I am not a clown. I am a professional safecracker. You also make balloon swords. Remember the circus? It was a hobby. It is a skill set now. Put on the red nose. They expect a performer. It smells like strawberries. Great. I feel like a dessert. If I get caught, I say I am lost. You will not get caught. We are ghosts. Silent, invisible ghosts. Ghosts do not steal presents. Ghosts steal dreams. I am stealing dreams wrapped in cellophane. The dog is out there. The dog is a toy. I saw it moving. It is a robotic Beagle. It is barking. It is recording. Listen. See? It is looping. Perfect. If the mom asks about the balloons. Tell her the air was too heavy. Time to move. Stay low. Keep your breathing shallow. I cannot breathe shallow. Too much air. Then hold it. I am going to pass out. Just walk. Act like you own the yard. I do not own the yard. Pretend you do. They respect property owners. Okay. I am doing it. Wait. Wait. What? Look at the tree. What about the tree? The ornaments are fake. It is a plastic tree. We need the gold ones. They are in the basement. We planned to get the toys. Plans change. Let's steal the tree too. It is heavy. We have wheels. We take the lot. We leave the mom with a plastic tree and some rocks. She will notice. She will blame Santa. Come on. Let's go.
created_at
"2026-02-25T23:39:45.449Z"
2/25/2026, 11:39:45 PM
model
"qwen/qwen3.5-35b-a3b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
469
moderation_latency
(null)
generation_time
37490
tokens_prompt
77
tokens_completion
4943
native_tokens_prompt
76
native_tokens_completion
5420
native_tokens_completion_images
(null)
native_tokens_reasoning
4892
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
0.010859
router
(null)
provider_responses
0
endpoint_id
"48c1210f-b7d2-4688-a340-f7424fc99d2b"
id
"chatcmpl-5803e567-26d4-9f4f-a7e0-d05820583c49"
is_byok
false
latency
469
model_permaslug
"qwen/qwen3.5-35b-a3b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772062785-1QtnzKwoKnx0vaBjP8X4"
upstream_id
"chatcmpl-5803e567-26d4-9f4f-a7e0-d05820583c49"
total_cost
0.010859
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
404
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 50.00%
neededClean
false
wordsTotal
404
wordsDialogue
0
0.0000%