NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK12NYMEP8DZKBYFBBX7XTJ
Run Details
Model:
Qwen 3.5 397B A17B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
6m 6s
Cost:
$0.049322
Provider:
Alibaba
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"Do you realize," Bill said, wiping sweat, "we are roasting a kindergarten?" "It's a heist, Bill. Focus on the objective." "There are clowns, Molly. Actual painted clowns." "Clowns don't have thumbs. They can't call the cops." "What about the parents? Tiger moms are really vicious." "They'll be distracted by the cake cutting. That's our window." "I feel sick. These are Lego sets, not diamonds." "Resale value is huge. Unopened boxes only, remember." "And the bounce house? It's a massive security nightmare." "It's camouflage. We jump inside, hide among the balls." "Plastic balls, Molly. They make noise when you shift." "Wear socks. Soft soles. Move slowly." "I'm stealing a piƱata. That bat looks heavy." "Don't get greedy. Stick strictly to the gift table." "There's a pony, Molly. A live pony outside." "We can't fence a pony. It leaves evidence." "I could ride it away during the diversion." "No horses. Just presents. Keep it clean." "Fine. But I'm taking the cake. I need sugar." "Eat it later. Now move. The magician is starting." "This is the lowest point of my career." "Think of the commission. Fifty percent each." "I hate children. They scream too much." "Less talking, more wrapping paper. Let's go."
created_at
"2026-02-16T10:55:05.699138+00:00"
2/16/2026, 10:55:05 AM
model
"qwen/qwen3.5-397b-a17b-20260216"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1019
moderation_latency
(null)
generation_time
365929
tokens_prompt
77
tokens_completion
8734
native_tokens_prompt
76
native_tokens_completion
13688
native_tokens_completion_images
(null)
native_tokens_reasoning
13367
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0493224
router
(null)
provider_responses
0
id
"chatcmpl-d6972fa5-2b7e-960b-9838-14a30de7c82b"
status
200
is_byok
false
latency
1019
endpoint_id
"180484a2-e24b-495a-ba41-b34b680d5a9f"
provider_name
"Alibaba"
model_permaslug
"qwen/qwen3.5-397b-a17b-20260216"
api_type
"completions"
id
"gen-1771238938-gpOScMQ2v9gwvhnfYucz"
upstream_id
"chatcmpl-d6972fa5-2b7e-960b-9838-14a30de7c82b"
total_cost
0.0493224
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
words
200
66.3916%
Dialogue to Total Word Ratio
Ratio: 98.00%, Deviation: 8.00%
neededClean
false
wordsTotal
200
wordsDialogue
196
83.1958%