NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0MXE7JMVW4X8TNNS8NM58M
Run Details
Model:
GPT-5.5
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
9.5s
Cost:
$0.008795
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
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 Crumb & Clover’s door gave its tiny silver shiver just as the last tray of cinnamon knots came out of the oven. Rain stippled the front window, blurring Main Street into watercolor. “You’re early.” “Couldn’t sleep. Besides, your lights were on.” “My lights are always on at five.” “Not in the pantry.” A cooling rack clicked as it was nudged too hard. “I was looking for almond flour.” “In the locked pantry?” “The latch sticks.” “It was unlocked when I found it this morning.” Behind the counter, the bakery smelled of butter, yeast, and the sharp ghost of lemon zest. On the display case, between the scones and seed cake, sat a single blue button. “That yours?” “I wear aprons, not sailor suits.” “Funny. Mayor Whitcomb’s jacket was missing a blue button last night.” “A lot of people own blue buttons.” “A lot of people weren’t heard arguing with him behind the bakery.” The rain thickened. Somewhere in back, the old mixer gave a settling groan. “He wanted the recipe.” “For cinnamon knots?” “For the deed to this building. Said he’d found something in Aunt Mae’s papers.” “And now he’s dead.” A soft thud came from the flour bin. “Tell me that was a mouse.” “Depends. Do mice hide envelopes?”
created_at
"2026-04-24T21:04:15.105Z"
4/24/2026, 9:04:15 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1485
moderation_latency
(null)
generation_time
9389
tokens_prompt
81
tokens_completion
378
native_tokens_prompt
67
native_tokens_completion
282
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"
usage
0.008795
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0ab3bb4110b798500169ebdacf40a48190b60b48de2c71feba"
is_byok
false
latency
351
model_permaslug
"openai/gpt-5.5-20260423"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777064655-PeMRL2ldW0bpA9ozt2F4"
session_id
(null)
api_type
"completions"
id
"gen-1777064655-nePC0SKnrX20a1MWTuTK"
upstream_id
"resp_0ab3bb4110b798500169ebdacf40a48190b60b48de2c71feba"
total_cost
0.008795
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)