NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36R050B8A8Y9PPVFN5V88VT
Run Details
Model:
GPT-6 Luna (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
40.8s
Cost:
$0.002012
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
98.51%
Dialogue to Total Word Ratio
(details)
99.2553%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
At eleven forty, the community hall resembled a cupcake after an argument with gravity. Paper streamers drooped from the ceiling, and a dinosaur guarded the door with the confidence of security. Molly crouched quietly behind a hedge of balloon animals, studying the party through binoculars borrowed from Bill. “Midnight,” Molly whispered, “we enter through the bouncy castle.” Bill adjusted his tuxedo, which was really a waiter’s vest worn backward. “And leave before the magician discovers rabbit has our getaway map.” The map was printed on a napkin and featured an arrow labeled “probably here,” because Bill had drawn it during lunch. Their target, a mountain of wrapped gifts, sat beneath a banner reading HAPPY BIRTHDAY, which Molly considered tactless advertising. “Bring socks.” Bill produced two black masks, then revealed they were sleep masks decorated with smiling llamas. “Stealth,” he explained, “is mostly about confidence.” He demonstrated by tiptoeing into a shrub and emerging wearing a rose from its thorns. Inside, children shrieked as the magician pulled a rabbit from a hat. Molly nodded solemnly. The rabbit wore a tiny waistcoat and looked more qualified than either thief. They waited for the birthday song, their getaway plan resting on Bill’s head.
created_at
"2026-09-23T09:01:58.382Z"
9/23/2026, 9:01:58 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
8477
moderation_latency
(null)
generation_time
40481
tokens_prompt
75
tokens_completion
608
native_tokens_prompt
66
native_tokens_completion
4011
native_tokens_completion_images
0
native_tokens_reasoning
3745
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
"completed"
service_tier
"default"
usage
0.0020121
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1790154118-ijm1u0J1KPpmn3xfYov0"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790154118-UMbdHKkw4BXrA2mvY3yw"
upstream_id
"resp_0edd6082e12c8c0a016ab39586906087d1b2f7663375252f95"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_0edd6082e12c8c0a016ab39586906087d1b2f7663375252f95"
is_byok
false
latency
2008
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0020121
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
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
98.51%
Dialogue to Total Word Ratio
Ratio: 13.50%, Deviation: 3.50%
neededClean
false
wordsTotal
200
wordsDialogue
27
99.2553%