NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ8RR2NC6B3MEXW9D8HQXGQ
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
15.2s
Cost:
$0.000197
Provider:
Novita
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Rain tapped the awning of the cramped delivery van as Molly squinted through binoculars at the bouncy castle shimmering under a disco ball. “You said this was a *low-risk* job, Bill.” “It is. They’re six. What’re they gonna do, throw a juice box at us?” “They’ve got a piñata that looks like a dragon. That thing could blind you with candy corn.” Bill tugged on a ski mask three sizes too big. “We go in during the limbo contest. When their heads are low, ours are high. Simple.” “Simple? My cousin Greg tried a yogurt cup heist at a daycare and got subdued by a toddler with a sticky hand.” “That was Greg. We’re professionals.” “With stolen clown wigs and party hats?” “Distractions enhance believability. I *am* Uncle Bob from Saskatoon. You’re Aunt Marge with the contagious laugh.” “Which, by the way, I don’t have.” “You’ll figure it out. We grab the loot pile near the cake, duck behind the slide, vanish into the sprinkler zone.” “And if someone recognizes us?” “Everyone’s crying by minute twenty. No one sees anything.” “I still think stealing from kids is morally questionable.” “I donated to a charity last week.” “Which one?” “The Parking Ticket Debt Relief Fund.” “That’s not a charity!” “It should be. Now, do we look like loving relatives ready to sing the Alphabet Song?” Molly sighed. “We look like felons at a puppet show.” “Exactly. Showtime.”
created_at
"2026-03-25T10:31:12.729Z"
3/25/2026, 10:31:12 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
938
moderation_latency
(null)
generation_time
15158
tokens_prompt
77
tokens_completion
412
native_tokens_prompt
72
native_tokens_completion
328
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.00019672
router
(null)
provider_responses
0
endpoint_id
"cf186489-d252-4fb7-aca9-87ef7b557eff"
id
"6ca5713e8dca5aeea6147e1ceed5ffde"
is_byok
false
latency
938
model_permaslug
"qwen/qwen3-235b-a22b-07-25"
provider_name
"Novita"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774434672-tNeOmgJIUtoaXySGoiJS"
upstream_id
"6ca5713e8dca5aeea6147e1ceed5ffde"
total_cost
0.00019672
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
236
0.00%
Dialogue to Total Word Ratio
Ratio: 85.17%, Deviation: 35.17%
neededClean
false
wordsTotal
236
wordsDialogue
201
0.0000%