NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ70J7ES3KZ4Y19TC6ZATSQR
Run Details
Model:
Qwen 3.5 Plus (2026-04-20)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2m 56s
Cost:
$0.028098
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
50.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 smoothed the crumpled venue map across the damp picnic table while Bill nervously adjusted his oversized party hat. The stolen invitation sat between them, mocking their entire criminal reputation. We enter through the snack station, Bill muttered, tapping the blueprint. The guards only watch the metal gates. They will never suspect two adults wearing plastic crowns, Molly replied, drawing a red arrow. We grab the largest boxes, leave through the clown trailer, and vanish before the games start. Sounds foolproof until a child tackles us, Bill sighed, checking his balloon whip. Nonsense. Molly smiled and tossed a heavy sack onto the grass. Every great heist requires festive branding. Now stop shaking and memorize the cake schedule. The sun dipped behind the fence while crickets began their evening chorus. We split the loot evenly after the magician leaves, Molly whispered, securing her earpiece. I still think the bouncy castle entrance is safer, Bill countered, zipping his tracksuit. Fine, just remember to drop the lollipops near the exit, Molly ordered, clicking her radio. Bill nodded slowly and checked his wrist watch. A stray dog barked near the perimeter fence while shadows stretched across the lawn. Bill agreed. The plan was solid.
created_at
"2026-04-27T08:23:17.216Z"
4/27/2026, 8:23:17 AM
model
"qwen/qwen3.5-plus-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
717
moderation_latency
(null)
generation_time
176117
tokens_prompt
77
tokens_completion
9902
native_tokens_prompt
76
native_tokens_completion
11695
native_tokens_completion_images
(null)
native_tokens_reasoning
11437
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
0.0280984
router
(null)
provider_responses
0
endpoint_id
"8b4a0fbb-6705-4f8d-a7f1-ad18ecc0edbc"
id
"chatcmpl-5d1ac513-f84d-953b-b6cd-449e628219df"
is_byok
false
latency
717
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-1777278197-O11OBZqFy7njMTaYZSlf"
session_id
(null)
api_type
"completions"
id
"gen-1777278197-72p6VE3AchcbNxwKvb66"
upstream_id
"chatcmpl-5d1ac513-f84d-953b-b6cd-449e628219df"
total_cost
0.0280984
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 50.00%
neededClean
false
wordsTotal
200
wordsDialogue
0
50.0000%