NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBH6191AN11WFJ2772YDCPZ
Run Details
Model:
Qwen 3.5 122B
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
1m 5s
Cost:
$0.027931
Provider:
Alibaba
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 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 tapped the blueprint with a gloved finger. "So, the target is a seven-year-old." "A pivotal age," Bill replied, leaning against the van door. "Lots of expensive plastic." "What's the security like?" "Parents. Mostly tired ones. Some with phones." "Can we handle the parents?" "I brought tranquilizers." "Too heavy. We need speed." "Speed and stealth." "What about the balloons?" "Pop them." "With what?" "Shurikens." "We don't have shurikens." "Then we use teeth." "Bill, this is a heist, not a ninja movie." "It's a tactical operation." "It's a kindergarten." "Semantics." "What about the loot?" "I heard a PS5." "At a seven-year-old's party?" "Rich parents, Molly. Very rich." "And the rest?" "LEGOs. Barbies. A giant teddy bear." "The bear is a liability." "Why?" "It squeaks." "We can duct tape it." "Or leave it." "No, it's vintage." "It's polyester." "Listen, the timing is tight." "When do we go in?" "During cake." "Cake is sticky." "Cake is distraction." "I hate cake." "Then don't eat it." "I'll steal the candles." "Why?" "For the wax." "Bill, focus." "I am focused." "On candles?" "On profit." "Okay, the exit?" "Through the bouncy castle." "That's a death trap." "It's aerodynamic." "It's a plastic box." "It's our getaway vehicle." "We need a van." "We are in the van." "Right." "So, do we have a plan?" "We have a strategy." "Is there a difference?" "Yes." "Tell me." "Strategy involves math." "Plan involves luck." "I like luck." "I like math." "Compromise?" "We use the math to find the luck." "Sounds complicated." "It is." "Are we ready?" "Always." "Good." "Let's go steal some toys." "For the kids?" "For the fence." "Right." "No guilt?" "None." "What if they cry?" "Then we cry too." "That's dark." "It's honest." "Okay. Let's move." "Wait, one last thing." "What?" "Do we bring masks?" "Yes." "What kind?" "Clowns." "Clowns?" "It fits the theme." "It fits the nightmare." "Perfect." "Let's go." "Wait, the engine." "It's cold." "Warm it up." "It's an hour drive." "We have time." "The ice cream melts." "It's not about the ice cream." "It's about the loot." "The loot melts." "No, the ice cream melts." "Right. The ice cream." "Forget the ice cream." "I'm hungry." "We eat after." "After the party?" "After the fence." "Okay." "Molly?" "Yes?" "Do you think they'll miss us?" "Who?" "The parents." "They're on their phones." "Good point." "Let's roll."
created_at
"2026-02-25T23:12:12.07Z"
2/25/2026, 11:12:12 PM
model
"qwen/qwen3.5-122b-a10b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
450
moderation_latency
(null)
generation_time
64792
tokens_prompt
77
tokens_completion
7735
native_tokens_prompt
76
native_tokens_completion
8719
native_tokens_completion_images
(null)
native_tokens_reasoning
7967
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
0.0279312
router
(null)
provider_responses
0
endpoint_id
"33d466d1-d2f7-45ed-8ff3-fda7d2e32351"
id
"chatcmpl-ffd674d6-5349-9204-851c-ff14d60addce"
is_byok
false
latency
450
model_permaslug
"qwen/qwen3.5-122b-a10b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772061132-UhrS8exs5p4kJXBusbQq"
upstream_id
"chatcmpl-ffd674d6-5349-9204-851c-ff14d60addce"
total_cost
0.0279312
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
387
0.00%
Dialogue to Total Word Ratio
Ratio: 96.16%, Deviation: 26.16%
neededClean
false
wordsTotal
391
wordsDialogue
376
0.0000%