NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36R050EB99ZTBJE1JFFX77P
Run Details
Model:
GPT-6 Luna (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
25.7s
Cost:
$0.001182
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.32%
Dialogue to Total Word Ratio
(details)
99.6533%
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 midnight, Molly spread a stolen birthday invitation across the laundromat table, weighing its corners with two stolen cupcakes. The target was a suburban party, where thirty presents waited beneath a paper rainbow and one suspiciously alert golden retriever. Bill studied the hand-drawn map through a jeweler’s loupe. Their plan required stealth, timing, and disguises: Molly would pose as a magician’s assistant, while Bill would impersonate the delivery man whose van they had borrowed from a bakery. Unfortunately, the bakery van still displayed a giant frosted slogan: “WE DELIVER JOY.” Molly said, “Bring disguises; toddlers respect official-looking clipboards and laminated badges, apparently.” Bill replied, “Good. I’ll distract them with cake while you liberate loot.” He tapped the map at the garden gate, where a note warned, DOG BITES. “That’s manageable,” he whispered, packing a squeaky toy, three party hats, and a net. Molly checked the getaway route, which crossed a trampoline, skirted a pond, and ended at a cul-de-sac with no exit. She nodded gravely. Every great operation needed contingencies; theirs included pretending the presents were late returns. The retriever barked. Bill’s clipboard caught fire from a birthday candle, and the children cheered, assuming the entertainment had arrived.
created_at
"2026-09-23T09:01:58.351Z"
9/23/2026, 9:01:58 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4108
moderation_latency
(null)
generation_time
25420
tokens_prompt
75
tokens_completion
915
native_tokens_prompt
66
native_tokens_completion
2350
native_tokens_completion_images
0
native_tokens_reasoning
2070
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
0.0011816
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1790154118-M3TK5uDOSyGAMey2uTjc"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790154118-mzAqb3zOlx2aCuJpzHX7"
upstream_id
"resp_0defc0e70d831f57016ab3958690ec87d189153e74da8e2077"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_0defc0e70d831f57016ab3958690ec87d189153e74da8e2077"
is_byok
false
latency
518
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0011816
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
99.98%
Matches word count
n/a
neededClean
false
words
198
99.32%
Dialogue to Total Word Ratio
Ratio: 12.87%, Deviation: 2.87%
neededClean
false
wordsTotal
202
wordsDialogue
26
99.6533%