NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36P3NAAFYA7ZXVFCVSJVJEP
Run Details
Model:
GPT-6 Luna (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
11.7s
Cost:
$0.000287
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
60.65%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
The bell over the door gave a nervous jingle, though the morning was still. “Tell me you didn’t put the mayor’s pocket watch in the cinnamon rolls.” “If I had, the dough would be ticking.” “That’s not funny, Elsie.” “It’s a little funny, Martin. And the watch was on the counter when I opened.” The bakery smelled of cardamom and warm butter. Outside, rain stitched silver lines down Main Street; inside, a tray of scones cooled beside the empty brass hook where the town’s old clock key usually hung. “Someone came in after closing,”
Martin said
. “The back door was unlocked.” “Or someone never left.” A pause. The oven clicked as it cooled. “You’re thinking of the flour prints.” “I’m thinking they lead from the pantry to the office, then stop at the window.” “Which was painted shut last summer.” “Exactly.” Martin leaned over the counter, lowering his voice. “You found something, didn’t you?” Elsie slid a sugar-dusted envelope from beneath the till. Its flap bore a smear of blue icing. “Not the watch.” “Then what?” “A note. It says, ‘Ask who changed the clock before the storm.’” The bell jingled again. Both of them looked toward the door. No one stood there—only a fresh set of floury footprints, pointing in.
created_at
"2026-09-23T08:28:56.016Z"
9/23/2026, 8:28:56 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6744
moderation_latency
(null)
generation_time
11700
tokens_prompt
78
tokens_completion
616
native_tokens_prompt
67
native_tokens_completion
560
native_tokens_completion_images
0
native_tokens_reasoning
271
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
0.0002867
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790152136-8w2Dr3vVDNgiE1X666aZ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790152136-dAUUGVmiP728VL1euzgA"
upstream_id
"resp_02de53bafde56122016ab38dc833c887d18ecd855cd2477404"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_02de53bafde56122016ab38dc833c887d18ecd855cd2477404"
is_byok
false
latency
1284
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0002867
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
60.65%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"Martin said"