NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX41BBWDZ3RJHAMRYNQE8VZX
Run Details
Model:
GPT-5.6 Luna
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
3.7s
Cost:
$0.001993
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 jingled, though no one entered. “Please tell me you heard that.” “I heard it. I also heard Mrs. Pritchard say she saw a ghost in the flour room.” “She says that every time the cinnamon rolls burn.” “Which is often.” Mara lowered her voice. “Then why is the back door open?” Across the counter, Theo stopped polishing a pie server. Outside, rain silvered the quiet street of Bellwether, and the bakery’s windows glowed like little squares of honey. “I locked it at six.” “You locked it after Mr. Vale left?” “I locked it before Mr. Vale left.” “That’s not what I asked.” A soft thump came from the kitchen. Theo reached beneath the counter and produced a rolling pin. Mara stared at it. “You’re going to defend us with pastry equipment?” “It’s walnut. Very sturdy.” Another thump, followed by a scrape. They crept past trays of cooling biscuits and the towering wedding cake Mrs. Pritchard had ordered for her third husband. The flour-room door stood ajar. Mara pushed it wider. A small black cat sprang out, scattering flour across the floor. Behind it lay a single muddy boot—and Mr. Vale’s silver pocket watch. Theo exhaled. “So, not a ghost.” “No. But unless that cat robbed him, we have a mystery.” From the front shop came the bell again. This time,
a man whispered
, “Don’t move.” Neither of them did.
created_at
"2026-07-09T18:13:28.596Z"
7/9/2026, 6:13:28 PM
model
"openai/gpt-5.6-luna-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
383
moderation_latency
(null)
generation_time
3485
tokens_prompt
81
tokens_completion
401
native_tokens_prompt
67
native_tokens_completion
321
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
0.001993
router
(null)
provider_responses
0
endpoint_id
"eebea444-34a5-4642-a766-cb319471d33a"
id
"resp_0334d620039e7a43016a4fe4c8af9c8197ac1bd985c0e2edee"
is_byok
false
latency
235
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-1783620808-0w6TYadZKHtNs3AyXFwX"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620808-KLxpaYAT7OM7bpUALrVF"
upstream_id
"resp_0334d620039e7a43016a4fe4c8af9c8197ac1bd985c0e2edee"
total_cost
0.001993
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
"a man whispered"