NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX4082V0RJ7G87A5S1RWCV6M
Run Details
Model:
GPT-5.6 Luna (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
4.0s
Cost:
$0.002599
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
By seven o’clock, the ovens at Buttercup Bakery had warmed the whole of Maple Street, but a chill lingered beneath the flour-dusted counters. “Someone’s been in the office.” Mara paused with a tray of cinnamon knots balanced against her hip. “That’s impossible. I locked it myself.” “Then your lock has developed a fondness for mystery.” A muddy boot print crossed the storeroom floor, ending beside the safe. Its brass door stood open, though nothing appeared missing except a single blue recipe tin. Mara set down the tray. “That tin held Grandmother’s lemon-curd recipe.” “And the recipe is worth stealing?” “To the right person, it could win the Harvest Bake-Off. The prize is five thousand dollars.” Outside, the bell over the front door jingled. Both women froze. A man in a green raincoat stepped inside, glanced toward the office, and immediately turned around. “Good morning,”
Mara called brightly
. “Leaving so soon?” “Forgot something.” “Your boots, perhaps?” He looked down at the muddy soles, then bolted. The bell clattered as Mara hurried after him, but the rain had already swallowed his footsteps. Her friend returned with a fallen sugar sack and a triumphant smile. “At least he didn’t get the lemon curd.” Mara stared at the open safe. “No. He got something more important.” “What?” “The old tin wasn’t a recipe box. It was where Grandmother kept her list of secrets.”
created_at
"2026-07-09T17:54:12.457Z"
7/9/2026, 5:54:12 PM
model
"openai/gpt-5.6-luna-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1607
moderation_latency
(null)
generation_time
3422
tokens_prompt
81
tokens_completion
404
native_tokens_prompt
67
native_tokens_completion
422
native_tokens_completion_images
0
native_tokens_reasoning
108
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
0.002599
router
(null)
provider_responses
0
endpoint_id
"eebea444-34a5-4642-a766-cb319471d33a"
id
"resp_00f3c428d6d7625c016a4fe0449dd481959935785c0657334a"
is_byok
false
latency
324
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-1783619652-7dTRuQMYQOdJ95Ghyzxb"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783619652-sLz94hX6CkVYQsOqqH78"
upstream_id
"resp_00f3c428d6d7625c016a4fe0449dd481959935785c0657334a"
total_cost
0.002599
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
60.65%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"Mara called brightly"