NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HBR0GB2PVM2K5R9B24S9P6
Run Details
Model:
Qwen 3.8 Max (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
4m 49s
Cost:
$0.081686
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.98%
Dialogue to Total Word Ratio
(details)
99.9910%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 floor. “The bouncy castle blocks the kitchen door, the piñata hangs over the fence, and every child in that yard is a tiny witness.” Bill polished a spatula. “Tiny witnesses with juice-stained hands. I brought disguises.” “You brought two clown noses.” “Exactly. We’ll be entertainment. Nobody questions a clown carrying a sack of loot.” “Bill, that sack says stolen goods.” “It says laundry. I crossed out laundry with banana.” “Why banana?” “It was in my pocket. Focus. We enter during cake, grab the presents, exit through the hedge.” “The hedge has a gnome.” “Then we bribe the gnome.” “You cannot bribe garden pottery.” “Molly, I once bribed a mailbox. It kept quiet for weeks.” She pinched the bridge of her nose. “Fine. I distract the parents with a puppet show. You collect the gifts.” “Puppets are too slow. I’ll do a magic trick. Behold, the presents vanish.” “You’ll vanish into a birthday mum’s handbag.” “Worth it. What’s the signal if trouble comes?” “If trouble comes, I sneeze twice.” “And if real trouble comes?” “Then I sneeze, you scream, and we run like we forgot our own names.” Bill tucked the spatula into his belt. “I prefer heroic crawling.” “Heroic crawling gets frosting on your knees.” “Frosting is camouflage.” Molly checked her watch. “The cake candles are lit. This is our window.” Bill put on a red nose. “For luck.” “For suspicion.” “Suspicion is just confidence wearing a silly hat.” “That’s the dumbest thing I’ve ever heard.” “Say it while holding the gift bag.” “Fine. Let’s steal every present from those children.” “Say it softer.” “Let’s borrow every present from those children, indefinitely.” “Perfect.” Molly opened the van door. Music burst from the garden. A child shrieked with joy. Bill gulped. “They sound vicious.” “They’re six.” “Six is ancient in party years.” “Move.” They crept across the lawn, past balloons and a sign that read Welcome Timmy. Bill tripped on a toy dinosaur. “Did you alert the dinosaur?” Molly whispered. “I negotiated with it.” “Then negotiate with the piñata before it testifies.” Bill saluted, bumped the piñata, and candy rained onto the table. Every child turned. Molly smiled brightly. “Puppet show!” she yelled. Bill grabbed three gifts, froze, and whispered, “Is that real trouble?” Molly sneezed twice. Bill screamed anyway. A mother appeared by the fence. “Are you the entertainers?” she asked. Molly bowed. “We are the surprise auditors of fun.” Bill lifted a gift. “This parcel failed inspection.” “Why is it wrapped in dinosaurs?” “Because dinosaurs love birthdays.” “Sneeze signal,” Molly hissed. “I sneezed internally.” “Externally, Bill.” “Maybe allergies respect courage.” Children charged toward candy. The mother gasped. Molly grabbed the sack and kicked the gnome into the hedge. “The gnome is compromised,” Bill whispered. “Run,” Molly said. “Do we grab the cake?” Molly asked. “Only if it is portable,” Bill answered. “It is a cake.” “Then it is portable.” “You are impossible.” “I am professional.” “Where is it?” “Behind the gnome.”
created_at
"2026-09-02T15:28:03.606Z"
9/2/2026, 3:28:03 PM
model
"qwen/qwen3.8-max-20260803"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1164
moderation_latency
(null)
generation_time
289017
tokens_prompt
75
tokens_completion
10684
native_tokens_prompt
127
native_tokens_completion
13572
native_tokens_completion_images
(null)
native_tokens_reasoning
12771
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
0.081686
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788362883-FRRvdSIur0nJXsBp2k4u"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788362883-J4ZJwRJn3neVbx4yi4ZO"
upstream_id
"chatcmpl-d0d040c1-eee3-928f-9560-f16be0ade22f"
provider_responses
0
endpoint_id
"6332e9fd-e0c4-4cae-8c17-d25bc774864a"
id
"chatcmpl-d0d040c1-eee3-928f-9560-f16be0ade22f"
is_byok
false
latency
1164
model_permaslug
"qwen/qwen3.8-max-20260803"
provider_name
"Alibaba"
status
200
total_cost
0.081686
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
99.98%
Dialogue to Total Word Ratio
Ratio: 70.06%, Deviation: 0.06%
neededClean
false
wordsTotal
501
wordsDialogue
351
99.9910%