NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ6ZBV61SEASPBSZ8NT7FARN
Run Details
Model:
Qwen 3.5 Plus (2026-04-20)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 49s
Cost:
$0.017342
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
35.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
17.5011%
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
So, the piƱata protocol is a go? Molly whispered, adjusting her reindeer antlers. Bill checked his watch, a digital timer taped to a juice box. Negative. The laser grid is only streamers, but the guard dog is a three-year-old with a juice box. Nasty temper. I've seen him tackle a clown. I brought the distraction. The golden ticket replica? Good. But what about the loot distribution? Do we hit the toy chest or the snack table? Toy chest. The LEGO Dyson sphere is worth more than the cupcake. Plus, the glitter is a hazard. And the clown? Neutralized. Paid him in lollipops to wear a blindfold. When the balloon pops, you're grabbing the PS5 wrapped as a juice box. Right. I look ridiculous. You look like a pro. Just remember, Bill: no eating the evidence. No huffing the glitter. I make no promises regarding the glitter. Also, if a mom asks for a balloon animal, I'm blowing the joint. And the magician? He's asleep. The cake is drugged with warm milk. Focus, Bill. We're in for the presents, not the finger painting.
created_at
"2026-04-27T08:02:19.464Z"
4/27/2026, 8:02:19 AM
model
"qwen/qwen3.5-plus-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
734
moderation_latency
(null)
generation_time
108867
tokens_prompt
77
tokens_completion
5699
native_tokens_prompt
76
native_tokens_completion
7213
native_tokens_completion_images
(null)
native_tokens_reasoning
6959
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0173416
router
(null)
provider_responses
0
endpoint_id
"8b4a0fbb-6705-4f8d-a7f1-ad18ecc0edbc"
id
"chatcmpl-c6a83e27-2971-9b49-a3c6-8be877df6204"
is_byok
false
latency
734
model_permaslug
"qwen/qwen3.5-plus-20260420"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777276939-g0R5RwYRe6ttgGvjvaW3"
session_id
(null)
api_type
"completions"
id
"gen-1777276939-n9tmV4S0cmVApjKUFjAK"
upstream_id
"chatcmpl-c6a83e27-2971-9b49-a3c6-8be877df6204"
total_cost
0.0173416
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
35.00%
Matches word count
n/a
neededClean
false
words
182
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
184
wordsDialogue
0
17.5011%