NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ72487NC3T5SEF53PRZ9SJ0
Run Details
Model:
Qwen 3.6 27B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2m 54s
Cost:
$0.041644
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9995%
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
The security guard dozed off in a velvet beanbag chair. Molly adjusted her fake clown nose and checked her watch. Bill tapped the blueprint with a plastic spork. The afternoon sun slanted through the bunting, illuminating a suspiciously large stash of wrapped boxes stacked near the patio door. A toddler giggled near the inflatable castle while a parent snored on a folding chair. Molly smoothed her sequined jumpsuit and calibrated the magnetic lockpick. Bill checked his empty velvet sacks. The wind carried frosting and impending criminal activity. Bill packed the ribbon cutting shears while Molly verified the perimeter route and compass. We move at three o'clock, Bill whispered. The parents always nap after cake. I have already neutralized the glitter bomb, Molly replied. It is tragically effective against dogs. Do we really need the dinosaur onesies, Bill asked. Absolutely not, Molly said. We only want the actual presents. What about the juice boxes, Bill wondered. Leave them, Molly ordered. We are professionals. The alarm system runs on batteries, Bill noted. Easy enough. Then we slip in through the punch bowl, Molly confirmed. Remember the code phrase, Bill muttered. Purple dinosaur attacks at noon. Got it, Molly nodded. We ride at dawn.
created_at
"2026-04-27T08:50:36.414Z"
4/27/2026, 8:50:36 AM
model
"qwen/qwen3.6-27b-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
647
moderation_latency
(null)
generation_time
163958
tokens_prompt
77
tokens_completion
10018
native_tokens_prompt
76
native_tokens_completion
11555
native_tokens_completion_images
(null)
native_tokens_reasoning
11294
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
0.0416436
router
(null)
provider_responses
0
endpoint_id
"826cab4e-dc26-4472-83be-e4ddd5ebd2ab"
is_byok
false
latency
828
model_permaslug
"qwen/qwen3.6-27b-20260422"
provider_name
"Morph"
status
(null)
1
endpoint_id
"82097366-3a73-4790-ac36-f96ba9f6f577"
id
"chatcmpl-30a4581e-14e9-9f5a-bbfe-59a89a0b53d9"
is_byok
false
latency
647
model_permaslug
"qwen/qwen3.6-27b-20260422"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777279836-7BTCFDv25iqNpVN5J3kg"
session_id
(null)
api_type
"completions"
id
"gen-1777279836-G4pweXuiCG4VYlf2fxWQ"
upstream_id
"chatcmpl-30a4581e-14e9-9f5a-bbfe-59a89a0b53d9"
total_cost
0.0416436
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
201
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 50.00%
neededClean
false
wordsTotal
201
wordsDialogue
0
49.9995%