NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NR162AFPR2E7WB14NP1XK
Run Details
Model:
GPT-6 Luna
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.0s
Cost:
$0.000170
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
40.39%
Dialogue to Total Word Ratio
(details)
20.1931%
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 spread the floor plan across the bonnet of the getaway car. “The presents are beneath the balloon arch,” she whispered. Bill peered at the drawing upside down. “I thought that was the cake.” “It’s a balloon arch.” “Then why does it say CAKE?” “Because I drew the cake.” Across the street, the children’s party glittered with streamers, tiny paper crowns, and the sort of cheerful music that made Bill feel personally accused. Their target was a mountain of gifts beside the punch bowl. Molly had brought disguises: two enormous mascot costumes shaped like cheerful rabbits. Bill lifted his head through the rabbit’s neck. “I can’t see.” “You’ll fit right in.” “I’m a rabbit with a beard.” “Festive beard.” They approached the garden gate, hopping with the strained dignity of criminals pretending to enjoy exercise. A little girl waved. Bill waved back, knocking his rabbit ear into a wind chime. The chime rang. Every adult turned. Molly kept hopping. “Smile.” “I’m terrified.” “Exactly. Rabbits are.” Inside, Molly steered their bulky costumes toward the gifts while Bill distracted the children with a clumsy dance. It worked brilliantly until the birthday boy declared Bill his favorite rabbit and hugged him around the knees. Molly loaded presents into a laundry sack. Then the boy offered Bill a cupcake. Bill accepted it, because refusing would have looked suspicious. They escaped through the hedge with stolen gifts, frosting on Bill’s nose, and a handwritten invitation to next Saturday’s party tucked in Molly’s pocket.
created_at
"2026-09-23T08:22:34.951Z"
9/23/2026, 8:22:34 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2101
moderation_latency
(null)
generation_time
5993
tokens_prompt
75
tokens_completion
422
native_tokens_prompt
66
native_tokens_completion
326
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
0.0001696
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151754-hvT8wa7s1E72MYpjWZC1"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151754-9w1qKMl19m9sW1kukZr1"
upstream_id
"resp_051fd4f4fe46ae51016ab38c4b14d887d1ad9dd3f8c90ec9dc"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_051fd4f4fe46ae51016ab38c4b14d887d1ad9dd3f8c90ec9dc"
is_byok
false
latency
842
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0001696
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
248
40.39%
Dialogue to Total Word Ratio
Ratio: 19.76%, Deviation: 9.76%
neededClean
false
wordsTotal
248
wordsDialogue
49
20.1931%