NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M36NNNCR5H817A9GHTYG1JFA
Run Details
Model:
GPT-6 Luna (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
8.5s
Cost:
$0.000249
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 above the bakery door gave a nervous little jingle as rain swept in from Main Street. On the counter, beside a cooling tray of lemon buns, lay a silver cuff link dusted with flour. “Not one of ours.” Mara set down her mixing bowl. “Unless the dough has developed excellent taste.” Theo leaned over the counter, careful not to touch the cuff link. His other cuff was fastened with a plain wooden button. “Mr. Bell wore silver ones at the town council meeting.” “He also accused you of stealing his prize-winning sourdough starter.” “He accused everyone. The starter was in his own pantry.” A gust rattled the front window. Across the street, the clock tower struck three, though it was only half past two. Mara glanced up. “That clock’s been wrong all week.” “Maybe it’s trying to give someone an alibi.” She looked at him. He nodded toward the floury cuff link, where a tiny blue thread clung to the hinge. “Bell’s coat was blue,”
she said
. “And he left through the back door after the meeting.” Mara lifted the tray and slid the buns into the display case. “Then whoever dropped this came in after him.” The bell jingled again. A woman in a yellow rain hat entered, carrying a paper bag from the hardware shop. Theo’s smile disappeared. “Do you know her?” “Only that she buys twine every Tuesday.” “Today’s Thursday.” Mara reached for the cuff link. “Then I think we’d better ask what she’s tying up.”
created_at
"2026-09-23T08:21:17.343Z"
9/23/2026, 8:21:17 AM
model
"openai/gpt-6-luna-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3170
moderation_latency
(null)
generation_time
8502
tokens_prompt
78
tokens_completion
518
native_tokens_prompt
67
native_tokens_completion
484
native_tokens_completion_images
0
native_tokens_reasoning
154
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
0.0002487
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790151677-ZW1n45hJlcTkdMDYz5hc"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790151677-iff38eWQ8hYfwqxsetDk"
upstream_id
"resp_0f5d831c07b93b95016ab38bfd769c87d18148a2db92f9ad05"
provider_responses
0
endpoint_id
"05e94e02-b9c2-4bbb-ba55-4082ee9ad687"
id
"resp_0f5d831c07b93b95016ab38bfd769c87d18148a2db92f9ad05"
is_byok
false
latency
354
model_permaslug
"openai/gpt-6-luna-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.0002487
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
"she said"