NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HARN5VTYSTAWPKCMZ83GQK
Run Details
Model:
Qwen 3.8 Max (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
4m 40s
Cost:
$0.081320
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 flattened the birthday invitation against the van wall. "We need a plan," Molly said. Bill pointed at his notebook, where crayon circles suggested either maps or snacks. "I have one," Bill said. "We knock, say entertainment, carry bags." He mimed knocking with imaginary confidence. "That is not a plan," Molly said. "It has rhythm," Bill said. "It has stupidity." Molly pinched the bridge of her nose. Outside, a suburban garden glittered with streamers, balloons, and suspiciously small chairs. "The presents are in the bouncy castle," Molly said. "Why?" Bill whispered. "Because children hide treasure in fortresses." She adjusted her goggles. "You watched too many films." Bill checked his empty duffel. "You brought a hook," Molly replied. "It is multipurpose." He hooked a paper plate for demonstration. The plate sailed into the hedge. A squirrel looked deeply embarrassed. "We enter as magicians," Molly announced. "I cannot do magic," Bill said. "You can vanish when police arrive." She checked the invitation again. A banner across the lawn read Sir Reginald Rules. Sir Reginald was seven and owned a pony. "We need disguises," Molly said. "I am hat," Bill said. "You wear two hats." Molly stared at him. "It doubles my authority." He tipped both hats. Through the fence gap, a table displayed cake boxes, juice boxes, and present mountains. "The cake is enormous," Bill said. "Focus," Molly snapped. "We grab gifts while clown performs." Bill folded his notebook. "What if clown is real security?" Molly narrowed her eyes. "Clowns are never security," Bill said. "Then why does he have walkie talkie?" She pointed. "It is banana phone." Bill sounded wounded. "You are impossible," Molly said. "You are tall," Bill said. The clown waved a rubber chicken. The children screamed like tiny investors. "We use cake diversion," Molly said. "I will trip," Bill offered. "You always trip." Molly sighed. "This time strategically." Bill practiced falling against a mailbox. The mailbox made a metallic complaint. A dog began singing. "Then gifts vanish in frosting chaos," Molly said. "And we escape in pony cart." Bill grinned. "There is a pony?" Molly asked. "Of course there is." Bill produced a carrot. Somewhere beyond the fence, Sir Reginald demanded more balloons. Molly looked at the house, the bouncy castle, the cake, and Bill. He saluted with the piƱata hook. "Perfect," she whispered. They crept toward the gate as party music began. The bouncy castle squeaked like a guilty whale. Bill adjusted his two hats. Molly checked her sack. The clown bowed. The presents waited. Sir Reginald turned seven. The gate creaked. Molly counted backward. Bill whispered luck. The carrot vanished. Somewhere, a pony snorted. Molly imagined headlines about thieves defeated by frosting, ponies, and a man wearing two hats. Bill imagined glory, or at least cake in his pockets. The wind lifted a napkin that read Tiny Hands Only. It landed on Bill's shoe like a contract. He accepted the assignment. Molly opened the gate one careful inch. The hinges squeaked in protest. Bill mouthed apology.
created_at
"2026-09-02T15:10:56.198Z"
9/2/2026, 3:10:56 PM
model
"qwen/qwen3.8-max-20260803"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1141
moderation_latency
(null)
generation_time
280364
tokens_prompt
75
tokens_completion
10900
native_tokens_prompt
127
native_tokens_completion
13511
native_tokens_completion_images
(null)
native_tokens_reasoning
12803
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
0.08132
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788361856-gZNymqCSWdNy6D6ZBvxo"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788361856-05aTuM8szpkXMTHNSsMT"
upstream_id
"chatcmpl-78fa0c70-a6fc-9e21-9fd5-3b8b3c8426df"
provider_responses
0
endpoint_id
"6332e9fd-e0c4-4cae-8c17-d25bc774864a"
id
"chatcmpl-78fa0c70-a6fc-9e21-9fd5-3b8b3c8426df"
is_byok
false
latency
1141
model_permaslug
"qwen/qwen3.8-max-20260803"
provider_name
"Alibaba"
status
200
total_cost
0.08132
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%