NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ78HZJ7919EXCDDCZAP57BW
Run Details
Model:
Qwen 3.6 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
52.4s
Cost:
$0.017678
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9920%
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
Quietly, Molly adjusted her ghillie suit, which was actually just a heavily modified bathrobe stuffed with toilet paper. She peeked through the slit over the bakery window, watching the chaotic swirl of colorful pastel balloons and sugar-fueled six-year-olds. The target was clear: the massive mountain of shiny wrapping paper trembling behind the inflatable bouncer. Bill stood beside her, nervously clutching a modified vacuum cleaner hose taped to a dustpan. His clumsy fingers drummed against the plastic, leaving streaks of dark grease. The plan relied entirely on the decoy piñata, which they had rigged to explode with confetti at the precise moment the hostess turned to scream loudly at a runaway cupcake. Molly checked her watch, a device to dispense gummy bears and calculate exit velocities. "Focus, Bill!" she whispered urgently. "Once the dog eats the piñata, we get rolling quickly now!" Bill nodded, sweat beading on his forehead, tightening his grip. They had practiced this maneuver in the alley behind the laundromat, drilling until their shoulders ached and their souls wept. "Remember the rules: absolutely no sharing, please!" The heist depended on silence, speed, and absolutely no eye contact with the adults holding lattes. Molly signaled the start. Bill inhaled. Victory awaited.
created_at
"2026-04-27T10:42:57.741Z"
4/27/2026, 10:42:57 AM
model
"qwen/qwen3.6-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
630
moderation_latency
(null)
generation_time
52342
tokens_prompt
77
tokens_completion
10410
native_tokens_prompt
76
native_tokens_completion
11773
native_tokens_completion_images
(null)
native_tokens_reasoning
11494
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
0.0176785
router
(null)
provider_responses
0
endpoint_id
"2435bec9-c808-4f27-9fc8-12f3460d7b66"
id
"chatcmpl-625d4229-f8a2-9448-a761-eb953c136bc0"
is_byok
false
latency
630
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-1777286577-npzgw323PIoiN7Ioq1sb"
session_id
(null)
api_type
"completions"
id
"gen-1777286577-LwjsOoSYUM7Q7sMdPVOS"
upstream_id
"chatcmpl-625d4229-f8a2-9448-a761-eb953c136bc0"
total_cost
0.0176785
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
100.00%
Dialogue to Total Word Ratio
Ratio: 9.76%, Deviation: 0.24%
neededClean
false
wordsTotal
205
wordsDialogue
20
99.9920%