NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-22-01KS86TVDBNHZVP6R2155S0RR6
Run Details
Model:
Qwen3.7 Max
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 39s
Cost:
$0.058105
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 unrolled the blueprint across the sticky diner table, smoothing the edges with her thumb. The schematic detailed a suburban backyard, complete with a bouncy castle and a petting zoo. Bill sipped his lukewarm coffee, studying the layout with intense focus. He adjusted his glasses, pointing at a small rectangular structure near the patio. That was the gift table. Hundreds of wrapped boxes sat there, waiting for a group of screaming toddlers to tear them apart. They needed a solid extraction route. Molly tapped her pen against the map, outlining a path through the sprinkler system. Timing was absolutely crucial. The parents would be distracted by the magic show, giving them a narrow window of opportunity to slip in and out unnoticed. Bill nodded slowly, understanding the immense risks involved in this ridiculous operation. Stealing from a bank was simple, but infiltrating a birthday celebration required absolute precision and nerves of steel. Molly leaned forward, her eyes narrowing as she finalized the strategy. She took a very deep breath and looked directly at her loyal partner. "We grab the paper donkey, smash it, and bag gifts." Bill frowned. "What about the angry clown?" Molly smiled. "I brought a cream pie."
created_at
"2026-05-22T16:03:29.337Z"
5/22/2026, 4:03:29 PM
model
"qwen/qwen3.7-max-20260520"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
965
moderation_latency
(null)
generation_time
99359
tokens_prompt
77
tokens_completion
5568
native_tokens_prompt
76
native_tokens_completion
7722
native_tokens_completion_images
(null)
native_tokens_reasoning
7472
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
0.058105
router
(null)
provider_responses
0
endpoint_id
"6d30fdc6-f2a7-4bdf-b6ba-32353496d723"
id
"chatcmpl-4eb1640f-a5e1-9c67-8c73-0a69f4cdab0a"
is_byok
false
latency
965
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-1779465809-oyt0Tuqc558jtX2mXJ9K"
session_id
(null)
api_type
"completions"
id
"gen-1779465809-k9IzbwgQwi2m15sdVMCL"
upstream_id
"chatcmpl-4eb1640f-a5e1-9c67-8c73-0a69f4cdab0a"
total_cost
0.058105
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%