NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KZYRZPE9A9CNA37XGVHT8Q
Run Details
Model:
Qwen 3.8 27B (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 48s
Cost:
$0.027655
Provider:
Io Net
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
51.89%
Dialogue to Total Word Ratio
(details)
75.9435%
Overall
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
"Molly, we break into the children's party," Bill whispered. "Great. We steal all presents right now." "The cake is a distraction." "Exactly. I cut the streamers like a ninja." "Ninjas don't wear glitter." "Then I'm a glitter ninja." "Kids will suspect." "We'll tell them we're birthday inspectors." "Inspecting what?" "Presents. Obviously." "Can you pick the lock?" "It's a ribbon." "Ribbon locks are dangerous." "I have a tiny crowbar." "It's a fork." "Forks are elegant tools." "The clown might return." "Tell him we moved the punch to the attic." "He lives in the punch?" "Metaphorically." "We need a signal." "A balloon animal?" "Too visible." "The piƱata screaming." "It can't scream." "Then the clown screams." "Plan approved." "May the best thief win." "May the presents be many." "Molly, do you have bags?" "I have a laundry basket." "Glamorous." "The most glamorous." "Should we leave polite notes?" "Absolutely. We're professionals." "Professional thieves with excellent manners." "Also, we must avoid the table confetti." "It traps the ankles." "I brought socks." "Nice." "Comfort is tactical." "Comfort is our getaway vehicle." "Smart." "Indeed." "Bill, the parents are here." "Then we run." "After we steal." "Exactly." "Three, two, one, present." "Let's go." "Hurry, before the sprinkles fall."
created_at
"2026-09-03T15:59:45.663Z"
9/3/2026, 3:59:45 PM
model
"qwen/qwen3.8-27b-20260814"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
409
moderation_latency
(null)
generation_time
107543
tokens_prompt
75
tokens_completion
7215
native_tokens_prompt
118
native_tokens_completion
9021
native_tokens_completion_images
(null)
native_tokens_reasoning
6873
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
service_tier
(null)
usage
0.027655236
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788451185-1txklaPMPm4qBipX1hYj"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788451185-vBp6Mf7T3hBDYMvYIaLh"
upstream_id
"chatcmpl-3c8ce28f-cb7f-439b-855c-f61223b75961"
provider_responses
0
endpoint_id
"c65c4547-63a7-49fb-8354-a45d118663c3"
id
"chatcmpl-3c8ce28f-cb7f-439b-855c-f61223b75961"
is_byok
false
latency
409
model_permaslug
"qwen/qwen3.8-27b-20260814"
provider_name
"Io Net"
status
200
total_cost
0.027655236
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Io Net"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
51.89%
Dialogue to Total Word Ratio
Ratio: 99.00%, Deviation: 9.00%
neededClean
false
wordsTotal
200
wordsDialogue
198
75.9435%