NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ6Z5Z6EW8ZCSF028RG6FR6X
Run Details
Model:
Qwen 3.5 Plus (2026-04-20)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 34s
Cost:
$0.014978
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
47.9934%
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
Focus, Molly hissed, stabbing the flyer. Johnson's party. Four PM. Clowns, cake, unsecured loot. Loot? Bill adjusted his colander-and-pantyhose mask. Shiny wrappers? Precisely. Grab the sack, sprint the hedge, and fence the rare Lego sets at the pawn shop before the kid blows his nose on a candle. Defense? Bill whispered, eyes watering. Lasers? Ninjas? Worse. A toddler with nuclear-powered juice and a dad battling the karaoke machine. The gift table is guarded only by an inflatable dinosaur, right next to the glitter cannon. Glitter? Static! Remember the jewelry job? I spent a month finding diamond grit in my ear canal and other sensitive geological formations. That was a win! Wear the poncho. You're the distraction? I pose as the magician. I palming the gifts into a hollowed-out piñata while doing sleight of hand. You're muscle, ready to restrain any weeping children who notice the disappearance. Grappling? Wrong. Piñata sticks? We accept the bruises for the payout! The trampoline launches us to the treeline. Bounce, scoop, vanish. I have back pain and a mortgage. Suck it up. Tonight we feast on unboxed toys and early retirement. Hands in. One, two, three: Heist!
created_at
"2026-04-27T07:59:06.964Z"
4/27/2026, 7:59:06 AM
model
"qwen/qwen3.5-plus-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
693
moderation_latency
(null)
generation_time
94075
tokens_prompt
77
tokens_completion
5900
native_tokens_prompt
76
native_tokens_completion
6228
native_tokens_completion_images
(null)
native_tokens_reasoning
5930
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
0.0149776
router
(null)
provider_responses
0
endpoint_id
"8b4a0fbb-6705-4f8d-a7f1-ad18ecc0edbc"
id
"chatcmpl-23d519f0-1d5d-9472-9841-1a244f9d772f"
is_byok
false
latency
693
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-1777276746-JNv4oSv58X3NjXo2SqkO"
session_id
(null)
api_type
"completions"
id
"gen-1777276746-HopBDYO2ukVXlQp3QgIR"
upstream_id
"chatcmpl-23d519f0-1d5d-9472-9841-1a244f9d772f"
total_cost
0.0149776
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
192
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
196
wordsDialogue
0
47.9934%