NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX41AMG9173ZY7ESV72NVYDK
Run Details
Model:
GPT-5.6 Luna (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
14.2s
Cost:
$0.015510
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
83.49%
Dialogue to Total Word Ratio
(details)
91.7457%
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
Molly checked the balloon bouquet and whispered, “Tonight, Bill, we infiltrate the birthday fortress.” “Fortress? It’s a suburban house with balloons.” “Our target?” “All the presents. We leave no glitter-wrapped treasure behind.” “Molly, these are children’s gifts.” “Exactly: small packages, low security, excellent resale value.” “Resale value?” “Fine, terrible resale value. But imagine the ransom notes.” “That’s not a heist. That’s bullying.” “It’s temporary redistribution of whimsy.” “You promised cake.” “After the operation.” “You promised that last time.” “We found a candle stuck to your hat.” “What’s the plan?” “I enter disguised as a magician.” “You can’t do magic.” “I can make a wallet disappear.” “Usually into your pocket.” “Details. You enter as the clown.” “I refuse to wear those shoes.” “They’re part of the disguise.” “They’re bigger than the getaway car.” “Then we flee on foot.” “Through a party full of children?” “Children are easily distracted.” “By what?” “Like presents?” “Your plan is to distract them with the presents we’re stealing?” “You understand the elegance.” “I understand we’re idiots.” “Partners, Bill.” “Fine. One present, replaced by a potato. We donate the rest.” “Why a potato?” “Nobody suspects produce.” “Everyone suspects produce at a birthday party.” “Then we’ll bring cake.”
created_at
"2026-07-09T18:13:04.656Z"
7/9/2026, 6:13:04 PM
model
"openai/gpt-5.6-luna-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
11376
moderation_latency
(null)
generation_time
13911
tokens_prompt
77
tokens_completion
595
native_tokens_prompt
66
native_tokens_completion
2574
native_tokens_completion_images
0
native_tokens_reasoning
2273
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
0.01551
router
(null)
provider_responses
0
endpoint_id
"eebea444-34a5-4642-a766-cb319471d33a"
id
"resp_0c775f35be83c9b6016a4fe4b0b9588196adc808d2f8e2d4b3"
is_byok
false
latency
215
model_permaslug
"openai/gpt-5.6-luna-20260709"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1783620784-smZeVSDCRYCztmqTdoSr"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620784-k9h4SnlhlYZ6C4zo8W0b"
upstream_id
"resp_0c775f35be83c9b6016a4fe4b0b9588196adc808d2f8e2d4b3"
total_cost
0.01551
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
83.49%
Dialogue to Total Word Ratio
Ratio: 96.52%, Deviation: 6.52%
neededClean
false
wordsTotal
201
wordsDialogue
194
91.7457%