NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NWM2MTV89WHEDT54BC0A7
Run Details
Model:
GPT-6 Luna
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
4.8s
Cost:
$0.000164
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 bakery door jingled, and rain followed Nora inside, stippling the flour-dusted floor. “Your usual?” asked a voice from behind the counter. “Tea and a cinnamon bun. Unless the buns have been behaving suspiciously.” “Only one vanished after closing.” Nora glanced toward the empty tray. “A bun doesn’t vanish. Someone takes it.” “Not according to Mrs. Bellweather. She says the ghost of the old miller is hungry.” “Does the ghost leave crumbs?” “Crumbs, yes. And a blue button.” Nora set down her umbrella. “That sounds less like a ghost and more like a coat with poor fastenings.” A thump sounded in the kitchen. “You locked the back door?” “Of course.” The kitchen door eased open. A ginger cat padded out, carrying something golden in its mouth. It dropped the missing bun at Nora’s feet and sat down, smug as a judge. “Well,” said Nora, “your ghost has whiskers.” “And a taste for cinnamon.” A second thump came from the kitchen, followed by a startled sneeze. Nora leaned toward the doorway. “Perhaps the ghost has a baker.” “Or the baker has a secret.” They exchanged a look. Outside, thunder rolled over the rooftops, while somewhere beyond the swinging door, someone began humming the miller’s old tune. “Tea first,”
Nora said
. “Then we investigate.” “Good. I’d hate to solve a mystery on an empty stomach.”
created_at
"2026-09-23T08:25:05.373Z"
9/23/2026, 8:25:05 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1711
moderation_latency
(null)
generation_time
4742
tokens_prompt
78
tokens_completion
378
native_tokens_prompt
67
native_tokens_completion
315
native_tokens_completion_images
0
native_tokens_reasoning
0
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
0.0001642
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151905-yS6ROed79hoH5ad8KXzR"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151905-XWu89CQ12zK3vJygBNgv"
upstream_id
"resp_0f8d5b6da999a00f016ab38ce178f887d18b21bc4b42352fa3"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_0f8d5b6da999a00f016ab38ce178f887d18b21bc4b42352fa3"
is_byok
false
latency
566
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0001642
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
"Nora said"