NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NKJF8R7WP2NZFVB67H7WN
Run Details
Model:
GPT-6 Luna (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
25.6s
Cost:
$0.001283
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.92%
Dialogue to Total Word Ratio
(details)
99.9495%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 crouched behind the hedge, wearing a tuxedo jacket over pajamas and clutching a clipboard upside down with grim determination. “Party ends at four, Bill. We enter at three fifty-nine, collect presents, and vanish before anyone notices the missing magician.” Bill studied the backyard through binoculars, which were actually two toilet-paper tubes taped together with festive stickers and glitter everywhere. “I object to stealing from children,” Bill whispered. “They have sticky fingers, unpredictable parents, and apparently a pony waiting beside the cake.” A chorus of tiny voices erupted inside, followed by a crash and the unmistakable squeak of a balloon animal nearby. “Relax. We’ll disguise ourselves as entertainers. You juggle; I’ll perform ventriloquism with the gift bags and blame the dummy afterward.” Molly handed him three oranges. Bill dropped all three, then bowed as if gravity had requested an encore politely, twice. “The children are applauding,” Molly said. “Excellent. Nothing says professional entertainer like a man losing a fight with citrus publicly.” They marched through the gate, where a papier-mâché dragon guarded a mountain of brightly wrapped boxes and one suspicious cupcake. “New plan: we’re hired guests. I’ll compliment the cake; you distract the adults by challenging the pony to chess outside.”
created_at
"2026-09-23T08:20:08.814Z"
9/23/2026, 8:20:08 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6207
moderation_latency
(null)
generation_time
25579
tokens_prompt
75
tokens_completion
1241
native_tokens_prompt
66
native_tokens_completion
2552
native_tokens_completion_images
0
native_tokens_reasoning
2282
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
0.0012826
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151608-bI6G2MZUPCM3llyObbWN"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151608-rzpzTkSytm828JGT0zir"
upstream_id
"resp_0f5572e71459336f016ab38bb91ce487d1ab40f6a8a495fc24"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_0f5572e71459336f016ab38bb91ce487d1ab40f6a8a495fc24"
is_byok
false
latency
555
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0012826
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
202
99.92%
Dialogue to Total Word Ratio
Ratio: 48.29%, Deviation: 1.71%
neededClean
false
wordsTotal
205
wordsDialogue
99
99.9495%