NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-22-01KS874YXK7PJJXJREK0EQA61V
Run Details
Model:
Qwen3.7 Max
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 18s
Cost:
$0.043382
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 adjusted her clown nose and checked the blueprint of the suburban backyard. The target was a seventh birthday celebration, heavily guarded by distracted parents and a wild mob of toddlers. Bill sat beside her in the unmarked van, carefully folding a map of the inflatable obstacle course. They had spent three weeks studying the gift table, noting the exact placement of the most expensive electronic toys. The plan was simple but required perfect timing. They would infiltrate during the musical chairs distraction, swap the wrapped boxes with identical decoys filled with broccoli, and vanish before the cake cutting. Bill wiped cold sweat from his forehead, clearly nervous about the risk of encountering a rogue balloon animal. Molly patted his shoulder, offering a reassuring smile beneath her thick white clown makeup. She pointed toward the side gate, signaling that the coast was finally clear. The music started playing loudly outside, clearly indicating the game had begun. They grabbed their oversized sacks and stepped out into the bright afternoon sun, ready to execute the absolute greatest toy robbery in modern history. "We absolutely need a much bigger bag for the bouncy castle exit. Just grab the giant dinosaur pinata thing too."
created_at
"2026-05-22T16:09:00.61Z"
5/22/2026, 4:09:00 PM
model
"qwen/qwen3.7-max-20260520"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
916
moderation_latency
(null)
generation_time
78350
tokens_prompt
77
tokens_completion
4720
native_tokens_prompt
76
native_tokens_completion
5759
native_tokens_completion_images
(null)
native_tokens_reasoning
5523
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
0.0433825
router
(null)
provider_responses
0
endpoint_id
"6d30fdc6-f2a7-4bdf-b6ba-32353496d723"
id
"chatcmpl-9f9b679b-80ef-996d-878d-e4d6da8b8eaf"
is_byok
false
latency
916
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-1779466140-n1znJBWTGp6NytPdb87X"
session_id
(null)
api_type
"completions"
id
"gen-1779466140-2JHsvkp6oz4ouaK6LqLP"
upstream_id
"chatcmpl-9f9b679b-80ef-996d-878d-e4d6da8b8eaf"
total_cost
0.0433825
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%