NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36R5E9KC5EP6N8MZM20GF7S
Run Details
Model:
GPT-6 Luna (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
37.6s
Cost:
$0.001767
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.95%
Dialogue to Total Word Ratio
(details)
99.9747%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
“The invitations say the party ends at six,” Molly whispered, “and the presents stay in the hall.” “Perfect,” Bill said. “We slip in, collect every box, and vanish before anyone notices.” “Your disguise is a clown?” “It’s a children’s party.” “Clowns are alarming.” “Then why are you wearing a mustache on your forehead?” “Disguise redundancy.” Molly peered through the window. “Wait. Those labels say ‘Molly’ and ‘Bill.’” “Maybe our names are popular.” “Bill, these are our own presents. We’re at the wrong house.” “Then whose party is ours?” “The one across the street, where we were invited.” “Why didn’t you say?” “I thought the clown gave it away.” “Fine. We’ll leave these gifts and go to our party.” “And explain the empty gift bag?” “Tell them we brought suspense.” A small child opened the door. “Are you the entertainment?” “Bill, perform the disappearing act.” “Gladly. You first.” “Where’d Bill go?” “Bill, that’s not disappearing. That’s hiding behind a dinosaur.” “It’s large.” “Come out and help pass out presents.” “Pass them out?” “Yes. We’ve become the entertainment.” “And after the show?” Bill asked. “We’ll accept applause instead of loot.” “And perhaps cake, if we confess before the frosting arrives, wearing sunglasses.”
created_at
"2026-09-23T09:04:51.517Z"
9/23/2026, 9:04:51 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
19845
moderation_latency
(null)
generation_time
37552
tokens_prompt
75
tokens_completion
530
native_tokens_prompt
66
native_tokens_completion
3520
native_tokens_completion_images
0
native_tokens_reasoning
3220
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
0.0017666
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1790154291-MlNfpeG2d9LZOudcUwtT"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790154291-Kf1LK7f4xe8glQo8N9QJ"
upstream_id
"resp_018cb20cb0837ad3016ab396339e3887d1bcd0244084316455"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_018cb20cb0837ad3016ab396339e3887d1bcd0244084316455"
is_byok
false
latency
1283
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0017666
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
99.95%
Dialogue to Total Word Ratio
Ratio: 91.50%, Deviation: 1.50%
neededClean
false
wordsTotal
200
wordsDialogue
183
99.9747%