NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NPP1QZJ2EWDS96J59E95S
Run Details
Model:
GPT-6 Luna
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.0s
Cost:
$0.000156
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.03%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
50.0145%
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
Molly studied the party through the hedge. Beyond the garden gate, balloons bobbed above a table piled with brightly wrapped presents. A clown performed a card trick for six children and one deeply suspicious toddler. “Is this really worth prison?” Bill whispered. “It’s worth the bicycle,” Molly whispered back. “I saw the tag.” Their plan was simple: sneak in dressed as entertainers, distract the guests, and escape with the gifts in Bill’s enormous balloon-animal basket. The plan became less simple when Molly’s costume shed glitter onto a sleeping guard dog. The dog opened one eye. Bill froze, holding a red balloon halfway twisted into a giraffe. Molly smiled at the dog with the desperate warmth of someone greeting an angry landlord. The clown spotted them. “New performers?” “Surprise act,” Molly said, stepping into the garden. The children cheered. Bill began making balloon swords. Molly redirected the guests toward the cake, then slipped behind the gift table. A little girl watched her lift a box. “That’s my present for Sam.” Molly lowered it. The box had a hand-drawn dinosaur and a crooked bow. For one inconvenient moment, she remembered being six. Bill quietly replaced the stolen gifts. Then he joined the children in a balloon-sword battle, where the toddler defeated him soundly. They left empty-handed, glittering, and pursued by the dog—which, Molly admitted, was probably the best haul of all.
created_at
"2026-09-23T08:21:50.784Z"
9/23/2026, 8:21:50 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1873
moderation_latency
(null)
generation_time
5974
tokens_prompt
75
tokens_completion
377
native_tokens_prompt
66
native_tokens_completion
299
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
0.0001561
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151710-dAdMFB2Dq2a251jOBAjg"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151710-png2eDQld1WHMF9oKToq"
upstream_id
"resp_0138365937a61cb0016ab38c1ee60087d1a7615b67bfd48a37"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_0138365937a61cb0016ab38c1ee60087d1a7615b67bfd48a37"
is_byok
false
latency
430
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0001561
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
0.03%
Matches word count
n/a
neededClean
false
words
230
100.00%
Dialogue to Total Word Ratio
Ratio: 9.40%, Deviation: 0.60%
neededClean
false
wordsTotal
234
wordsDialogue
22
50.0145%