NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NHTVE25M9W2NMPR55WHTS
Run Details
Model:
GPT-6 Luna (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
25.9s
Cost:
$0.001252
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
99.9950%
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
Rain tapped the windows of the community hall while Molly spread a floor plan across the bonnet of her stolen hatchback. The map showed lanterns, frosting, and unsupervised toddlers. Their target was every present, before anyone noticed. Behind the party room’s banner, a mountain of wrapped presents waited beneath the coat rack, guarded by one exhausted parent and a balloon shaped like an angry swan. “Tonight, we enter as clowns,” Molly whispered. Bill adjusted his bow tie, which had gravy on it from a job involving a wedding cake and a surprised groom. “Children distrust clowns,” Bill said. Molly frowned. “Then wear balloons; nobody suspects balloons,” Molly replied. Their entry strategy depended on blending into the party, although neither owned a costume, and Bill considered a bedsheet “basically theatrical.” The back door stood open for deliveries. A papier mâché dragon blocked the hallway, its painted nostrils smoking from a hidden cupcake warmer. Bill eyed it nervously. “I’m allergic to subtlety,” Bill muttered. Molly handed him three yellow balloons and a clipboard labeled PARTY INSPECTOR. “Perfect,” said Molly, “probably.” They marched toward the door, practicing their cheerful faces. Bill’s looked like a man apologizing to a fish. Inside, children began singing.
created_at
"2026-09-23T08:19:11.86Z"
9/23/2026, 8:19:11 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
16902
moderation_latency
(null)
generation_time
25838
tokens_prompt
75
tokens_completion
587
native_tokens_prompt
66
native_tokens_completion
2490
native_tokens_completion_images
0
native_tokens_reasoning
2217
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
0.0012516
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151551-9htsnwv4LIkbBh45CaZi"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151551-jtASNENqljvyVq726lTG"
upstream_id
"resp_0480aa26128c47d8016ab38b7ffc8887d18816dabfe135d526"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_0480aa26128c47d8016ab38b7ffc8887d18816dabfe135d526"
is_byok
false
latency
448
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0012516
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
99.99%
Dialogue to Total Word Ratio
Ratio: 11.00%, Deviation: 1.00%
neededClean
false
wordsTotal
200
wordsDialogue
22
99.9950%