NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0P97DMDSPTEBZBXD1G277C
Run Details
Model:
GPT-5.5
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
8.3s
Cost:
$0.008735
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 Sugar Maple Bakery’s door gave its usual sleepy jingle as rain tapped against the front windows. Behind the glass case, lemon bars sat in perfect yellow squares, and a tray of cinnamon rolls steamed beside the register. “You’re early.” “You always say that when I arrive before the muffins cool.” “That’s because respectable people wait for muffins to cool.” “Respectable people don’t hide envelopes under sacks of flour.” A wooden spoon clattered against the counter. “I don’t know what you mean.” “You left a dusting of flour on the seal. And your name is printed on the corner.” “That envelope is none of your business.” “It became my business when Mrs. Bellweather’s sapphire brooch turned up in the donation basket, wrapped in one of your pastry papers.” Outside, a truck hissed through a puddle. Inside, the bakery smelled of sugar, yeast, and something sharper—fear. “I didn’t steal anything.” “I didn’t say you did.” “Then why are you looking at me like that?” “Because whoever put the brooch there wanted everyone to look at you.” The oven timer chimed, bright and cheerful. “You believe me?” “I believe cinnamon rolls don’t lie, and yours were rising when the church fair started.” “That’s the strangest alibi I’ve ever had.” “It may also be the sweetest.”
created_at
"2026-04-24T21:28:09.916Z"
4/24/2026, 9:28:09 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1336
moderation_latency
(null)
generation_time
8167
tokens_prompt
81
tokens_completion
387
native_tokens_prompt
67
native_tokens_completion
280
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
0.008735
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0846035da399753f0169ebe06a27448195801090d440ec1627"
is_byok
false
latency
496
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-1777066089-X0Hcg8pMVWTgxlh1bF8T"
session_id
(null)
api_type
"completions"
id
"gen-1777066089-wx8JjWWz4lUnEZDLLnIQ"
upstream_id
"resp_0846035da399753f0169ebe06a27448195801090d440ec1627"
total_cost
0.008735
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)