NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-26-01KJBM21ZZEQZE06Z5YK8N87WP
Run Details
Model:
Qwen 3.5 35B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
57.0s
Cost:
$0.018993
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9995%
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
Bill whispered nervously, clutching a rubber glove. Are you absolutely sure about this? This is a birthday party, not a high-security vault. It’s a goldmine. Look at the wrapping. All that shiny paper. That is pure inventory. What about the noise? They’re screaming. Kids scream incredibly loud right now. We scream louder. Or we just hide under the table like rats. Elegant rats with huge canvas duffel bags. Elegant rats don’t carry duffel bags. And where exactly in the world are we getting the bags? The trash bins outside. We raid the recycling bins. The parents might check the trash. They’ll be too busy with the cake. Distraction is our weapon. Blow out the candles, grab the loot, vanish into the smoke. Smoke? There is no smoke. Candles make smoke. Now check your clown nose again. It is terribly crooked. I hate this job. Please be careful. Hate it while you count the cash. Yes I know. Thirty short seconds. Are you really ready right now? Ready. If we get caught, we tell them it’s an acting class. Perfect. Now move. Before the ice cream melts completely. Bill took a deep breath. Molly checked her watch slowly. They stood in shadows.
created_at
"2026-02-26T00:02:27.46Z"
2/26/2026, 12:02:27 AM
model
"qwen/qwen3.5-35b-a3b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
438
moderation_latency
(null)
generation_time
56874
tokens_prompt
77
tokens_completion
7214
native_tokens_prompt
76
native_tokens_completion
9487
native_tokens_completion_images
(null)
native_tokens_reasoning
9202
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
0.018993
router
(null)
provider_responses
0
endpoint_id
"48c1210f-b7d2-4688-a340-f7424fc99d2b"
id
"chatcmpl-4437bee1-e673-93ab-b165-50d394b96193"
is_byok
false
latency
438
model_permaslug
"qwen/qwen3.5-35b-a3b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772064147-yMnGZUeUx6lv7TeQX16U"
upstream_id
"chatcmpl-4437bee1-e673-93ab-b165-50d394b96193"
total_cost
0.018993
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
201
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
202
wordsDialogue
0
49.9995%