NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ73GWNV1YP1GJ7W2HGRG55H
Run Details
Model:
Qwen 3.6 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 59s
Cost:
$0.028292
Provider:
Morph
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
63.6358%
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 basement air smelled like melted plastic and desperate birthday wishes. Molly adjusted her tactical goggles, which were mostly useful for filtering out sparkles. She traced the blueprints across a wobbly folding table. The house plans showed a perimeter of inflatable dinosaurs and a soft play zone that would swallow their boots entirely. Bill knelt beside her, carefully polishing a lockpick next to a half eaten fruit snack. He wore a black turtleneck that clashed violently with his neon green sneakers. Their target was the suburban bungalow hosting a massive seventh birthday celebration for a boy who apparently owned three identical laser tag arenas. The security was notoriously chaotic, featuring a single teenage cousin manning the front porch with a clipboard and zero authority. Molly tapped the blueprint near the gift table, her finger hovering over a stack of aggressively wrapped boxes. Bill nodded slowly, checking his watch while a distant balloon animal squeaked in protest. They needed to slide through the laundry window, bypass the cake smearing vigilantes, and grab every single present before the piƱata shattering protocol began. The clock ticked loudly on the microwave above them. They waited. Secure the glitter cannons instead of the paper plates. Agreed, but keep the juice box route perfectly clear today.
created_at
"2026-04-27T09:14:59.139Z"
4/27/2026, 9:14:59 AM
model
"qwen/qwen3.6-27b-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
946
moderation_latency
(null)
generation_time
118923
tokens_prompt
77
tokens_completion
9656
native_tokens_prompt
76
native_tokens_completion
11771
native_tokens_completion_images
(null)
native_tokens_reasoning
9320
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
0.0282922
router
(null)
provider_responses
0
endpoint_id
"826cab4e-dc26-4472-83be-e4ddd5ebd2ab"
id
"4bceff46c4df4f1897559100950e8990"
is_byok
false
latency
838
model_permaslug
"qwen/qwen3.6-27b-20260422"
provider_name
"Morph"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777281299-dfnp6gvVhLM2hn2DGGI6"
session_id
(null)
api_type
"completions"
id
"gen-1777281299-NhUMKWPHCg6vZnaniZPR"
upstream_id
"4bceff46c4df4f1897559100950e8990"
total_cost
0.0282922
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Morph"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
210
36.79%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 10.00%
neededClean
false
wordsTotal
210
wordsDialogue
0
63.6358%