NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36P47Z6FMBJB8T5XGMZ70J1
Run Details
Model:
GPT-6 Luna
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
7.2s
Cost:
$0.000178
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
18.3940%
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 spread the floor plan across the bonnet of their getaway car. “The party’s in the community hall. Presents are stacked beside the birthday cake.” “Excellent,” said Bill. “We enter disguised as entertainers.” “You can’t juggle.” “I can juggle one thing.” “What?” “My expectations.” Molly tapped the map. “We go through the kitchen, grab the gifts, and leave before anyone notices.” “Children notice everything,” Bill said. “Last week one spotted my fake mustache was attached with jam.” “Then we need a better disguise.” Bill opened the boot. Inside lay two enormous costumes: a smiling rabbit and a slightly sinister cupcake. “I’ll be the rabbit,” he said. “Rabbits are trusted.” “Not that rabbit. It looks like it knows where the bodies are buried.” “That’s the cupcake, Molly.” She sighed. “Fine. We’ll pose as party helpers. You carry the presents; I distract the adults.” “With what?” “Conversation.” “Terrifying.” They slipped around the back and entered through the kitchen. A woman handed Molly a tray of lemonade. “Perfect,” Molly whispered. “We’re in.” Bill eyed the glittering pile of gifts. “Operation Wrapped Up is underway.” A small voice spoke behind him. “Are you the magician?” Bill froze. “Yes.” “Make my uncle disappear.” Molly smiled. “That’s our specialty.” Bill hefted a gift sack. “Can we start with this one?” “No,” Molly whispered. “The uncle.” From the hall came a thunderous snore. “Lucky,” Bill said. “He’s already vanishing into his chair.”
created_at
"2026-09-23T08:29:15.117Z"
9/23/2026, 8:29:15 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2212
moderation_latency
(null)
generation_time
7140
tokens_prompt
75
tokens_completion
442
native_tokens_prompt
66
native_tokens_completion
343
native_tokens_completion_images
0
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)
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
0.0001781
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790152155-L2cQVUo7wDw4i0ivcNuR"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790152155-LNiWGt63SHi5oCMW7vd7"
upstream_id
"resp_0ef85b7a3e508248016ab38ddb343c87d1ae74be40742324eb"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_0ef85b7a3e508248016ab38ddb343c87d1ae74be40742324eb"
is_byok
false
latency
984
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0001781
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
0.00%
Matches word count
n/a
neededClean
false
words
235
36.79%
Dialogue to Total Word Ratio
Ratio: 60.00%, Deviation: 10.00%
neededClean
false
wordsTotal
235
wordsDialogue
141
18.3940%