NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBKATG22GHJ5967M1Y9VCWR
Run Details
Model:
Qwen 3.5 35B
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
35.9s
Cost:
$0.012941
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
14.72%
Dialogue to Total Word Ratio
(details)
7.3590%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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
The rain fell hard on the inflatable castle as twenty kids screamed inside. Molly adjusted her mask behind the hedge while Bill checked the lockpicks under his coat. He looked nervous, his eyes darting toward the door where the sound of party music thumped. "Are we sure this is legal?" "We'll see. Focus on the exit route." "There are no exits. Only the door." "Then we go through the door. Push past the cake." "Bill, the cake has a candle. It is a lit flame." "It is a distraction. They cannot see us if they are blowing out candles." "That is logic for toddlers, not adults." "Logic is for accountants. This is for us." "We need to grab the bikes first. They are heavy." "We need to grab the gift bags. They are light." "Bikes fit in the back of the van. Bags don't fit in a pocket." "Then we take the bikes." "I have gloves." "I have a backpack." "Where are we hiding?" "Behind the bushes. If we fall in, we roll." "What if the dad comes out?" "We say we are part of the magic show." "He won't know what to do." "He will be confused. Confusion is time." "Time is what we need." "Okay, let's do this." "Wait. The dog." "Which dog?" "The golden retriever. It is looking at us." "Don't look it in the eye. It is a challenge." "It is wagging." "It is waiting for treats. Throw it one." "I don't have treats." "Throw a rock." "That is not nice." "It is a heist. It is nice to steal. Not nice to pet." "The plan changes." "We change. The plan stays." "Okay. One minute." "Wait." "What?" "The music is loud." "So?" "We cannot hear ourselves think." "We are too late." "We are exactly on time." "You are insane." "I am professional." "Professional thieves do not rob kids." "Kids have the best presents. Adults just get socks." "I got socks last year." "And this year?" "A toaster." "We can sell the toaster for three hundred." "It is a gift." "Everything is a gift if we sell it." "The door opened." "Go." "Wait." "Why?" "The dog ran over." "Good. Distraction." "He licked me." "We go now." "I am going." "Good luck." "Don't say that." "Okay. Good luck." Molly held her breath as the heavy metal gate rattled against the hinges. She checked her watch. Two minutes. The rain soaked her jacket completely. Bill nodded once, a sharp movement in the shadows. "Did you hear that?" "Did you see that?" "Go." "Wait. One more thing." "What?" "Do we need to tip the dog?" "We do not tip the dog." "But he helped us." "He is a criminal accomplice now." "He is a good dog." "He is a thief's dog." "Okay. Dog is thief." "Now we go." "Yes." The children cheered inside the house as the thunder rumbled overhead. Bill adjusted his coat and walked toward the van. Molly followed slowly, clutching the plastic bag. They had ten minutes before the parents noticed the presents were missing. It would be enough time. They were professionals. "Stop." "Why?" "I dropped a coin." "Leave it." "It might ring." "Then pick it up." "I can't bend down." "Bend down." "I won't." "Go." "Okay." They vanished into the night.
created_at
"2026-02-25T23:49:46.121Z"
2/25/2026, 11:49:46 PM
model
"qwen/qwen3.5-35b-a3b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
434
moderation_latency
(null)
generation_time
35819
tokens_prompt
77
tokens_completion
6238
native_tokens_prompt
76
native_tokens_completion
6461
native_tokens_completion_images
(null)
native_tokens_reasoning
5624
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
0.012941
router
(null)
provider_responses
0
endpoint_id
"48c1210f-b7d2-4688-a340-f7424fc99d2b"
id
"chatcmpl-a9551503-2f94-9a2f-946d-2de005a151ca"
is_byok
false
latency
434
model_permaslug
"qwen/qwen3.5-35b-a3b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772063386-WBQRdH1BL8J3NErFQ6mM"
upstream_id
"chatcmpl-a9551503-2f94-9a2f-946d-2de005a151ca"
total_cost
0.012941
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
546
14.72%
Dialogue to Total Word Ratio
Ratio: 76.19%, Deviation: 6.19%
neededClean
false
wordsTotal
546
wordsDialogue
416
7.3590%