NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0NNA86K4E71Z5TSVJCJDGK
Run Details
Model:
GPT-5.5
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
8.6s
Cost:
$0.009305
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 & Comfort’s door gave its usual tinny jingle, lost beneath the patter of rain and the hum of the old display case. Warm cinnamon wrapped around the room like a quilt. “You’re dripping on my clean floor.” “I was dripping outside too, but nobody complained there.” “That’s because the statue of the town founder has better manners than you.” “And less reason to be worried.” A tray of lemon scones slid onto the counter, their glaze still glossy. Beyond the front windows, Main Street blurred silver and gray. “Worried about what?” “About the mayor’s missing watch.” “The one he waved around at the harvest raffle like it was the crown jewels?” “That’s the one. He says it vanished right after he left here yesterday.” “People lose things all the time.” “People don’t usually find them baked into Mrs. Pritchard’s rye.” The oven ticked in the sudden quiet. “You’re joking.” “I wish I were. She cut it open at breakfast and nearly swallowed the minute hand.” “Well, that explains the constable sniffing around my flour bins.” “Did he find anything?” “Only that his uniform is too tight for crouching.” A laugh broke the tension, brief and bright as the bell. “Still, somebody put it there.” “And whoever did knew our bread schedule.” “Exactly.” The rain kept falling, but inside, the bakery felt suddenly less cozy.
created_at
"2026-04-24T21:17:17.461Z"
4/24/2026, 9:17:17 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
899
moderation_latency
(null)
generation_time
8507
tokens_prompt
81
tokens_completion
405
native_tokens_prompt
67
native_tokens_completion
299
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
0.009305
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0d425f5819ae8aa10169ebdddd8db881948d67b6541520a155"
is_byok
false
latency
261
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-1777065437-Rj55OpOS0ScVRDmXR2FR"
session_id
(null)
api_type
"completions"
id
"gen-1777065437-Nm1jqtSBa7W6wW7yPad3"
upstream_id
"resp_0d425f5819ae8aa10169ebdddd8db881948d67b6541520a155"
total_cost
0.009305
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)