NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NQ2RR7K7CCHQHDDZAY7GW
Run Details
Model:
GPT-6 Luna (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
35.0s
Cost:
$0.001574
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
99.9968%
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 studied the party hall through borrowed binoculars. Paper stars trembled above windows, advertising tomorrow’s birthday with letters. Their target: every wrapped present stacked beneath the cake table. Their motive was rent; Molly nudged Bill, sharing concerns quietly. “The presents are guarded by six-year-olds and one suspicious balloon.” “I brought disguises, snacks, and a getaway tricycle with streamers.” Molly wore black, though her sweater featured conspicuous yellow ducks. Bill’s tricycle waited, its basket crowded with muffins and optimism. Their plan required quiet entry, gift collection, escape before cake. Molly checked the side door, which opened with one squeak. Bill lubricated it using butter stolen from a nearby picnic. Unfortunately, the hinges now smelled delicious, attracting a curious terrier. They waited while it investigated, then slipped inside like professionals. Cardboard pirate greeted them, brandishing foam cutlass with theatrical menace. Molly bowed; Bill saluted, nearly toppling from his tricycle helmet. Beyond, gifts formed a colorful mountain guarded by juice boxes. They filled sacks quickly, avoiding dolls whose eyes seemed judgmental. A toy car circled Bill’s ankle like an angry beetle. He froze as lights flickered on, revealing their excellent disguises. Molly’s ducks looked incriminating beneath the bright spinning disco ball.
created_at
"2026-09-23T08:22:03.806Z"
9/23/2026, 8:22:03 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
18672
moderation_latency
(null)
generation_time
34970
tokens_prompt
75
tokens_completion
1012
native_tokens_prompt
66
native_tokens_completion
3134
native_tokens_completion_images
0
native_tokens_reasoning
2856
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
0.0015736
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151723-QLRuWgExfJNgZH7G7fM4"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151723-ae8hGplgGXFtLueSxT3r"
upstream_id
"resp_05bde13bbb7f202b016ab38c2be2dc87d1809fc437a70f861e"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_05bde13bbb7f202b016ab38c2be2dc87d1809fc437a70f861e"
is_byok
false
latency
369
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0015736
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: 10.89%, Deviation: 0.89%
neededClean
false
wordsTotal
202
wordsDialogue
22
99.9968%