NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HCZ1FNJA8D8JCBCAX9F1K8
Run Details
Model:
Qwen 3.8 Max (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
3m 51s
Cost:
$0.063902
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 500 word scene that has 30% 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 and Bill crouched behind a striped hedge, wearing pastel disguises and extremely serious expressions. "We enter through the fence, smile at the parents, and locate the gift table." Molly checked a crayon map. Bill polished a pocket full of spare wrapping paper. "What if the clown sees us? Clowns always have suspicious pockets." A distant clown honked. Molly did not blink. "The clown is hired help. You distract him with balloon animals." Bill frowned at his gloved hands. "I am terrible at balloon animals. I make snakes look angry." She patted his shoulder with tactical sympathy. "Then make one angry snake and call it art." Bill glanced at a table covered in bright boxes. "Fine. What about the cake? A heist needs snacks." Molly adjusted her tiny fake mustache. "No cake. Cake is evidence with frosting." He looked wounded. "Evidence tastes sweet. I say we steal two slices." She pointed at the presents. "We steal presents, not dessert. Stay professional." He nodded solemnly. "Professional thieves eat cake after the job." Somewhere a child shrieked with delight. Molly considered this a security breach. "After the job, we vanish in a bubble machine." Bill became emotional. "A bubble machine? That is my dream escape." Molly silenced him with a party hat. "Then dream quietly. The birthday child is returning." He stretched like a villain warming up. "I will grab the gifts. You grab the joy." Molly closed her eyes briefly. "We do not grab joy. Joy is free." Bill grinned. "Then we grab presents and leave joy as a decoy." The hedge rustled. They both froze. Then Molly gave the signal. "Begin Operation Rush." They crawled toward the garden gate while balloons bobbed above them like cheerful guards. Molly whispered that every present had a name, and Bill whispered that every name had a ribbon. The bouncy castle thumped beside them, a bright fortress of air and chaos. A toddler wandered past holding a paper crown and a spoon. Molly waved with one finger. Bill waved with both hands, as if surrendering to cuteness. The gift table glittered under streamers. Each package seemed to pulse with expensive decisions made by tired relatives. They reached the tablecloth. Molly lifted a corner with theatrical care. Bill reached for a box shaped like a dinosaur. Molly slapped his hand. She selected a modest bag instead, because small crimes build discipline. Then the clown appeared around the corner, holding a balloon sword and a look of gentle suspicion. Molly smiled as if she had been invited. Bill smiled as if he had never stolen anything except possibly attention. The clown pointed at their shoes. They looked down. Both wore burglar masks with their party hats. Molly sighed. Bill shrugged. The clown honked once, then turned away, deciding they were part of the entertainment. They inched backward, dragging a sack of joy and one noisy package that sounded like regret. Somewhere behind them, a child yelled that the game was very realistic. Molly accepted the compliment.
created_at
"2026-09-02T15:49:22.557Z"
9/2/2026, 3:49:22 PM
model
"qwen/qwen3.8-max-20260803"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
884
moderation_latency
(null)
generation_time
230516
tokens_prompt
75
tokens_completion
8943
native_tokens_prompt
127
native_tokens_completion
10608
native_tokens_completion_images
(null)
native_tokens_reasoning
9941
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
0.063902
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788364162-qGKxgzx3uAfmYTz9XJAm"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788364162-RU0HDRD9WPrBnFUEwe26"
upstream_id
"chatcmpl-310ecc74-0ac9-9233-a41c-6f70dfc77a25"
provider_responses
0
endpoint_id
"6332e9fd-e0c4-4cae-8c17-d25bc774864a"
id
"chatcmpl-310ecc74-0ac9-9233-a41c-6f70dfc77a25"
is_byok
false
latency
884
model_permaslug
"qwen/qwen3.8-max-20260803"
provider_name
"Alibaba"
status
200
total_cost
0.063902
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
500
100.00%
Dialogue to Total Word Ratio
Ratio: 30.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
150
100.0000%