NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ77BSPGMJRT455AS9FDVMZ6
Run Details
Model:
Qwen 3.6 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
38.1s
Cost:
$0.012802
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.3561%
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
Molly adjusted her scratchy polka-dot dress, itching like neonatal mosquitoes. Bill fiddled with a backpack straining against contraband glow-in-the-dark bouncy castles. They crouched behind a tinsel tree smelling of regret and artificial fruit punch. The muffled thrum of "Baby Shark" vibrated the floorboards, a rhythmic assault testing their resolve. Molly checked her wrist, revealing a laser cutter disguised as a digital calculator. Bill wiped sweat from his brow, smearing glitter across his forehead. Terror didn't stem from security cameras, but from the mandatory sing-along. Molly nudged him with a gloved elbow, eyes fixed on the cardboard rectangles promising unearned joy. She drew lock-picking tools from her cracker gun. Bill hovered over a smoke bomb disguised as a party favor, his knuckles white. A balloon arch wobbled precariously. Molly's gloves squeaked, echoing like thunder in Bill's ears. He checked the raffle ticket, his only cover. The child monitor crackled with menacing laughter. Molly gripped her taser disguised as a juice box, eyeing the door. Molly whispered, "Remember," "we grab the Lego Death Star and move. No games, no singing." Bill clutched his nose. "Don't make me blow up the piƱata." Molly smirked. They held their breath before the door opened. The sugar-fueled riot approached. Time to strike.
created_at
"2026-04-27T10:22:06.552Z"
4/27/2026, 10:22:06 AM
model
"qwen/qwen3.6-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
613
moderation_latency
(null)
generation_time
37965
tokens_prompt
77
tokens_completion
7391
native_tokens_prompt
76
native_tokens_completion
8522
native_tokens_completion_images
(null)
native_tokens_reasoning
8217
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
0.012802
router
(null)
provider_responses
0
endpoint_id
"2435bec9-c808-4f27-9fc8-12f3460d7b66"
id
"chatcmpl-09bb3cd8-a771-9058-a623-f44f91a6f62e"
is_byok
false
latency
613
model_permaslug
"qwen/qwen3.6-flash"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777285326-gW5oHwOhv3prTVNGZIjg"
session_id
(null)
api_type
"completions"
id
"gen-1777285326-Yv57ajyJGjNvngHRJYDv"
upstream_id
"chatcmpl-09bb3cd8-a771-9058-a623-f44f91a6f62e"
total_cost
0.012802
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
206
100.00%
Dialogue to Total Word Ratio
Ratio: 10.33%, Deviation: 0.33%
neededClean
false
wordsTotal
213
wordsDialogue
22
99.3561%