NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ8AB89K3ESK2QJA90D2486
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.5s
Cost:
$0.000206
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.97%
Dialogue to Total Word Ratio
(details)
49.9863%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 moon hung low like a lopsided disco ball as Molly crouched behind a dumpster overflowing with half-eaten cupcake wrappers and deflated balloons shaped like cartoon dinosaurs. Bill adjusted his ski mask, which had slipped over one eye, giving him the look of a particularly confused raccoon. Between them, sprawled across a grease-stained drop cloth, lay an elaborate blueprint drawn on the back of a pizza box. It detailed the backyard layout of Timmy Henderson’s seventh birthday party, where, according to Molly’s “in-the-know” source (a disgruntled clown fired for excessive tootling), one hundred and three lightly used presents awaited—each wrapped in glitter-infested paper and guarded only by a piñata dragon and a sleep-deprived parent or two. Molly pointed to a crayon-annotated zone labeled “Cake Zone (High Risk).” Sweat dripped down her temple from wearing a full bee costume as camouflage. "We go in during the musical chairs collapse," she whispered, eyes gleaming like a fox contemplating a henhouse. "Panic is our ally. Chaos is our caterer." Bill nodded solemnly, clutching a pillowcase adorned with spaceships. It fluttered in the breeze like a banner of absurd ambition. Nearby, a squeaky toy penguin blinked red lights in rhythm with the neighbor’s motion light. They shared a look—equal parts madness, mirth, and mild concern about whether glitter was, in fact, the devil’s dandruff—then crawled forward on elbows and knees, leaving behind only crumbs and bad decisions.
created_at
"2026-03-25T10:23:20.845Z"
3/25/2026, 10:23:20 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
495
moderation_latency
(null)
generation_time
6434
tokens_prompt
77
tokens_completion
388
native_tokens_prompt
72
native_tokens_completion
326
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.000205712
router
(null)
provider_responses
0
endpoint_id
"813ce28a-1334-47e3-881e-a7f8833b34b4"
id
"chatcmpl-93d3ebee-6826-92bf-8d77-658593d4cb6f"
is_byok
false
latency
495
model_permaslug
"qwen/qwen3-235b-a22b-07-25"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774434200-DqJcewUcIwXq3fKdcoEJ"
upstream_id
"chatcmpl-93d3ebee-6826-92bf-8d77-658593d4cb6f"
total_cost
0.000205712
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
236
99.97%
Dialogue to Total Word Ratio
Ratio: 8.71%, Deviation: 1.29%
neededClean
false
wordsTotal
241
wordsDialogue
21
49.9863%