NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ7QRFK7SS71VAM4VCEDZ7T
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
6.1s
Cost:
$0.000047
Provider:
WandB
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 drummed on the awning above the dingy alley where Molly hunched over a crayon-scribbled map taped to a dumpster. Molly: “You really think a castle bounce house is stable enough for the escape?” Bill: “It’s engineered to withstand tiny, sugar-fueled tornadoes. It’ll hold. Probably.” Molly: “Probably? Our getaway plan depends on a plastic monarchy.” Bill: “Relax. In and out during the piñata. Chaos, distraction, grab the gift mountain near the clown throne.” Molly: “And if Timmy’s cousin spots us?” Bill: “Then we gift-wrap him and say he won a prize.” Molly: “I still don’t get why we’re robbing six-year-olds.” Bill: “Because no one ever suspects the balloon animals. Besides—those gifts are top-shelf. Remote-control dinosaurs, glitter slime labs. Rich kid birthday. Catered unicorn cake.” Molly: “That cake has a *horn*. How is that practical?” Bill: “It’s symbolic. Like our moral decline.” Molly: “You think they have good loot?” Bill: “I saw a gift tag say ‘To Timmy, From Santa (Again).’ That’s at least three gift layers deep.” Molly: “So we go in disguised as party staff?” Bill: “You’ll be ‘Aunt Linda.’ I’m ‘Uncle Bob’ with a fake mustache and a broken kazoo.” Molly: “Why the kazoo?” Bill: “It’s a key part of the emotional misdirection.” Molly: “You just want to play ‘Yakety Sax’ during the heist.” Bill: “It’s not a heist without a proper soundtrack.” Molly: “Fine. But if I get puked on by a unicorn cake, I’m cutting you out of the cut.” Bill: “Deal.”
created_at
"2026-03-25T10:13:11.991Z"
3/25/2026, 10:13:11 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
74
moderation_latency
(null)
generation_time
5713
tokens_prompt
77
tokens_completion
451
native_tokens_prompt
72
native_tokens_completion
399
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
0.0000471
router
(null)
provider_responses
0
endpoint_id
"c9f927db-d559-49eb-9846-80862c5e3b4e"
id
"chatcmpl-af3311ddd367227f"
is_byok
false
latency
26
model_permaslug
"qwen/qwen3-235b-a22b-07-25"
provider_name
"WandB"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774433592-vvPGpM62z4JgYE7yPrsh"
upstream_id
"chatcmpl-af3311ddd367227f"
total_cost
0.0000471
cache_discount
(null)
upstream_inference_cost
0
provider_name
"WandB"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
247
0.00%
Dialogue to Total Word Ratio
Ratio: 83.86%, Deviation: 33.86%
neededClean
false
wordsTotal
254
wordsDialogue
213
0.0000%