NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ903AT0JREXQE3W8RAB4HJ
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.9s
Cost:
$0.000197
Provider:
Novita
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
34.0511%
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
Molly crouched behind a plastic jungle gym, binoculars pressed to her face. "Still no sign of the piñata guard." Bill adjusted his ski mask, which read "I ♥ BALLOONS" in glitter. "You sure about this? Last time we hit a birthday party, we got chased by a clown with a squirting flower." "That clown had it coming. And this party’s got forty kids, at least thirty gift bags, and—get this—wrap check." "Wrap check?" "Yeah, the parents label the presents at the door. Organized. It’s like they *want* us to steal them." Bill scratched his head. "So we’re not dressing as clowns this time?" "No clowns. You’re a rogue magician. I’m a disgruntled birthday princess." "Which one?" "The one who didn’t get invited. It’s tragic. People eat that up." “Genius.” Bill zipped up his cape. “But how do we get past the face-painting station?” “Distract them with a poorly timed cartwheel. I’ll grab the loot.” “And the cake?” “We take the cake. It’s chocolate. Might cover the guilt.” Bill paused. “Do we *have* guilt?” “Only when the sugar wears off.” “Right. Operation: Tickle Me Theft is a go.” Molly stood, adjusting her plastic tiara. “And Bill?” “Yeah?” “Don’t eat the evidence this time.” “I can’t promise anything. Some wrapping paper is *tissue thin*.”
created_at
"2026-03-25T10:35:13.63Z"
3/25/2026, 10:35:13 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
850
moderation_latency
(null)
generation_time
8849
tokens_prompt
77
tokens_completion
377
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
"94fed8d4de1ea8cd77506e5e2e03aa99"
is_byok
false
latency
850
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-1774434913-rVLjhSIyW5T0Xjlqq5qd"
upstream_id
"94fed8d4de1ea8cd77506e5e2e03aa99"
total_cost
0.00019672
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
68.10%
Matches word count
n/a
neededClean
false
words
214
0.00%
Dialogue to Total Word Ratio
Ratio: 82.33%, Deviation: 32.33%
neededClean
false
wordsTotal
215
wordsDialogue
177
34.0511%