NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HCDYA6VXXZKPKH1WN7C6F2
Run Details
Model:
Qwen 3.8 Max (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
5m 14s
Cost:
$0.083648
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 spread the crayon map across the van hood, smoothing wrinkles left by a melted juice box. The bouncy castle loomed beyond the hedge like a pink fortress, and somewhere inside a clown was losing control of sixteen hyper children. "Okay," Molly said. "The target is a pile of gifts by the puppet stage. We enter through the balloon arch, pose as entertainment, and leave with every present." Bill adjusted a tiny party hat over his beanie. "I hate children. They notice things. Last time one asked why my mustache was a cat." "It was a cat." "It was emotional support. I kept it calm." Molly tapped the map. "Focus. You distract them with magic. I haul sacks." "My magic?" Bill said. "I only know the trick where I pull a coin from an ear, and I usually use my own ear." "Then use your own ear. Make it tragic." A banner reading HAPPY SEVENTH BIRTHDAY, KEVIN snapped in the wind. Molly had forged invitations, printed badges, and acquired a piñata filled with expired coupons, which she considered artistic overhead. "We need a code," Bill said. "We have one. It is Presents." "That is not a code. That is a motive." "Fine. If danger appears, shout pineapple." "Pineapple suggests danger?" "It suggests tropical urgency." They crept through the side gate. Inside the garden, streamers coiled around rosebushes, and a magician was being heckled by a child holding a spoon like a scepter. The present table glittered with ribbons, robots, dolls, and one suspiciously heavy box labeled DO NOT OPEN UNTIL KEVIN IS LESS SUSPICIOUS. Molly slid a satin sack from her coat. Bill produced a rubber chicken, then stared at it as if it had volunteered for the war. "I was supposed to bring doves," he whispered. "Where did you get a chicken?" "It came in the dove kit. I think they downsized." The magician vanished in a cinnamon flash, leaving a stage full of children and a table full of presents. Molly moved first, sliding parcels into her satin sack while Bill juggled the chicken, three candy canes, and a toy dinosaur. The toddler crown pointed again, but the room had become a whirl of sugar, parents, and one inflatable pirate ship losing air. Molly kicked a gift bag toward Bill. He caught it with his elbow, lost the chicken, and recovered it with the dignity of a man defying fate. A balloon popped. The party shuddered. Molly zipped the last sack as the piñata burst nearby, raining coupons like boring snow. Bill mouthed a solemn oath, grabbed a banner for balance, and accidentally rolled himself in crepe paper. They reached the gate together, sparkling, panting, and victorious. The van doors shut softly behind them, hiding the loot, the glitter, and the faint smell of birthday cake. "Go," Molly said. Bill lifted the squeaky giraffe like a sacred trophy, nodded once, wiped frosting from his chin, and whispered, "Together. Presents." They drove away into the glittering afternoon heat outside.
created_at
"2026-09-02T15:40:02.254Z"
9/2/2026, 3:40:02 PM
model
"qwen/qwen3.8-max-20260803"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1141
moderation_latency
(null)
generation_time
313969
tokens_prompt
75
tokens_completion
11584
native_tokens_prompt
127
native_tokens_completion
13899
native_tokens_completion_images
(null)
native_tokens_reasoning
13220
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
0.083648
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788363602-pLFYnNsZkiPobayHkdtP"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788363602-NcLAa1jD2thvaDHEKVnH"
upstream_id
"chatcmpl-e38e00e2-925f-924f-a2ac-84d0d7685e5e"
provider_responses
0
endpoint_id
"6332e9fd-e0c4-4cae-8c17-d25bc774864a"
id
"chatcmpl-e38e00e2-925f-924f-a2ac-84d0d7685e5e"
is_byok
false
latency
1141
model_permaslug
"qwen/qwen3.8-max-20260803"
provider_name
"Alibaba"
status
200
total_cost
0.083648
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%