NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ795A37Q2C57TFBNDQ7XK92
Run Details
Model:
Qwen 3.6 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
20.7s
Cost:
$0.006592
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
93.23%
Dialogue to Total Word Ratio
(details)
96.3032%
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
Molly adjusted her balaclava, checking the detonator watch. "Is that even legal?" Bill whispered. "Bill, it's grand larceny on a minor, not a traffic ticket. Now check the security feed." "They have a bouncy castle. The acoustics are going to be a nightmare." "Exactly. Perfect cover for the vanishing act. Did you pack the taser-tickle sticks?" "I brought the marshmallows instead. The kids love treats. Distraction strategy?" "Bill, we are master thieves, not clowns. Hand over the marshmallows. Where's the gift hoard located?" "Under the plastic tree. Surrounded by six screaming velociraptors and a mother with a stroller cannon." "Stroller cannon?" "It shoots sippy cups. High velocity. We need the jetpacks." "We're not getting jetpacks. We're getting the Big Blue Truck. You remember the route?" "Left past the piñata, drop from the chandelier, grab the truck, exit via the balloon animal airlock?" "Correct. Just don't touch the cat. It's the alarm system. And check for ninja bears." "What cat?" "That's why I said don't touch the cat! If the cat sneezes, the balloons explode. Also, remember Tim? Tim's in the piñata." "Why did nobody tell me about the explosives?" "Because you brought marshmallows! Now move, the singing teleports in three minutes and I hate polka."
created_at
"2026-04-27T10:53:31.119Z"
4/27/2026, 10:53:31 AM
model
"qwen/qwen3.6-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
763
moderation_latency
(null)
generation_time
20529
tokens_prompt
77
tokens_completion
4006
native_tokens_prompt
76
native_tokens_completion
4382
native_tokens_completion_images
(null)
native_tokens_reasoning
4046
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
0.006592
router
(null)
provider_responses
0
endpoint_id
"2435bec9-c808-4f27-9fc8-12f3460d7b66"
id
"chatcmpl-cf4500bc-5109-9f7e-8edb-3d48b989587d"
is_byok
false
latency
763
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-1777287211-aFSZaWfc61Ri0g1LSSeC"
session_id
(null)
api_type
"completions"
id
"gen-1777287211-ZHjdB0t9ev7bFe8Cemdi"
upstream_id
"chatcmpl-cf4500bc-5109-9f7e-8edb-3d48b989587d"
total_cost
0.006592
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
205
93.23%
Dialogue to Total Word Ratio
Ratio: 95.15%, Deviation: 5.15%
neededClean
false
wordsTotal
206
wordsDialogue
196
96.3032%