NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NN0Z75K5VWHM6K2851S62
Run Details
Model:
GPT-6 Luna (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
24.2s
Cost:
$0.001185
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 unfolded the map beneath a flickering streetlamp. She whispered, “The birthday fortress has one guard, and he is six.” Bill straightened his tie, hiding a grappling hook. He muttered, “Balloons worry me; one exposed my operation last time, badly.” Molly circled the window beside a party poster. She explained, “We enter quietly, collect every gift, then vanish before cake.” Bill tested suction cups against the florist’s van. He grinned, “A flawless plan, assuming gravity respects professional boundaries tonight, too.” Molly checked the clock and frowned at midnight. She warned, “The invitation says three, Bill; punctuality matters even during burglary.” Bill proudly produced his crown from his pocket. He replied, “Children trust crowns; I shall pose as their visiting monarch.” Molly examined his suspiciously stickered paper crown closely. She sighed, “Your Majesty, perhaps remove the barcode before greeting the children.” Bill peeled it off, sticking it on Molly. He promised, “Then we shall look like charitable guests, not suspicious professionals.” Molly heard tiny voices rehearsing a song inside. She froze, “Wait, Bill; guards are children, and they’re armed with glitter.” Bill lowered his sack, reconsidering his criminal career. He whispered, “Perhaps we should donate presents instead, then steal leftover cake.”
created_at
"2026-09-23T08:20:56.429Z"
9/23/2026, 8:20:56 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3795
moderation_latency
(null)
generation_time
24165
tokens_prompt
75
tokens_completion
723
native_tokens_prompt
66
native_tokens_completion
2356
native_tokens_completion_images
0
native_tokens_reasoning
2070
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
0.0011846
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151656-xqlwL2OOOPMKHp0s9qZj"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151656-Svq8AB3sNkv58Jh8L5X5"
upstream_id
"resp_02582ddc60691360016ab38be8852487d1b1e019aa2a34a203"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_02582ddc60691360016ab38be8852487d1b1e019aa2a34a203"
is_byok
false
latency
420
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0011846
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
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
100
100.0000%