NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0NPCQFPF4Y68VVDJ3BNZ6S
Run Details
Model:
GPT-5.5
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
9.1s
Cost:
$0.008915
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 the bakery door gave its usual cheerful jingle, though the fog pressed gray hands against the windows. Warm cinnamon and butter filled the little shop, wrapping around the empty tables and the display case of lemon tarts. “You’re early.” “Couldn’t sleep. Not after finding Mrs. Bell’s brooch in my flour bin.” “That sounds like the beginning of a confession, not an explanation.” “I didn’t take it. I was kneading dough when she was arguing with Mayor Pike outside the post office.” “Everyone was arguing with Mayor Pike yesterday. It was Founders’ Day.” “Not with their hands on his sleeve and tears in their eyes.” A tray slid into the oven; the metal racks chimed softly. “You noticed all that from here?” “I notice people. It’s good for business.” “And for solving murders?” The silence settled, sweet and heavy as glaze. “Dr. Finch said the mayor was poisoned.” “He bought a cherry Danish at eight-fifteen.” “From you?” “From the basket by the door. Self-serve.” “So anyone could’ve slipped something in.” “Anyone with a key. The basket is filled before I unlock.” The fog blurred a figure crossing the square. “Then why is Mrs. Bell’s brooch in your flour?” “Because whoever killed him wants me dusted, sifted, and baked before noon.”
created_at
"2026-04-24T21:17:52.759Z"
4/24/2026, 9:17:52 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
686
moderation_latency
(null)
generation_time
8993
tokens_prompt
81
tokens_completion
380
native_tokens_prompt
67
native_tokens_completion
286
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
0.008915
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_08466dcc94a241a00169ebde00d88881968ab673426362f0bf"
is_byok
false
latency
286
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-1777065472-aOocp6tWBnWbgCVUlI6U"
session_id
(null)
api_type
"completions"
id
"gen-1777065472-XWD58Iy2PyLdWcVal7oh"
upstream_id
"resp_08466dcc94a241a00169ebde00d88881968ab673426362f0bf"
total_cost
0.008915
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)