NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-22-01KS87ATSC4VCD9SMTWCH056X2
Run Details
Model:
Qwen3.7 Max
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 26s
Cost:
$0.049960
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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
Molly crouched behind the rhododendron bush, adjusting her tactical binoculars. The suburban backyard was a chaotic battlefield of screaming children, spilled juice boxes, and aggressive balloon animals. She mapped out the perimeter, noting the distracted parents near the barbecue grill. The pile of brightly wrapped gifts sat unguarded on the patio table, a glittering mountain of plastic and electronics. Bill knelt beside her, struggling to fold his large frame into the tiny plastic tricycle they had commandeered for the getaway. He checked his watch and sighed, wiping sweat from his forehead. The heist required absolute precision and perfect timing. Molly handed him a foam sword and pointed toward the inflatable structure. She took a deep breath, visualizing the escape route through the side gate. The wind shifted, carrying the scent of burnt hot dogs and cotton candy. Bill nodded solemnly, accepting his ridiculous disguise. Molly whispered her final instructions. She knew the sticky fingerprints of many angry children would be their greatest obstacle today. The birthday boy was already throwing a massive tantrum near the cake. Time was running out. "We will distract the noisy toddlers with the bouncy castle while you wear those oversized red clown shoes right now."
created_at
"2026-05-22T16:12:12.987Z"
5/22/2026, 4:12:12 PM
model
"qwen/qwen3.7-max-20260520"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
912
moderation_latency
(null)
generation_time
86120
tokens_prompt
77
tokens_completion
5173
native_tokens_prompt
76
native_tokens_completion
6636
native_tokens_completion_images
(null)
native_tokens_reasoning
6385
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"
service_tier
(null)
usage
0.04996
router
(null)
provider_responses
0
endpoint_id
"6d30fdc6-f2a7-4bdf-b6ba-32353496d723"
id
"chatcmpl-d523196e-3b3d-914c-8f67-dde843574b68"
is_byok
false
latency
912
model_permaslug
"qwen/qwen3.7-max-20260520"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.15.0; linux; x64))"
http_referer
(null)
request_id
"req-1779466332-mtivkTuNmQg1g04Ntjxz"
session_id
(null)
api_type
"completions"
id
"gen-1779466332-wnnby7XoP5MthLWOQX0R"
upstream_id
"chatcmpl-d523196e-3b3d-914c-8f67-dde843574b68"
total_cost
0.04996
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
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%