NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK96P3Y9YPNV9KMXT3FQVME
Run Details
Model:
GPT-5.1
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
14.3s
Cost:
$0.003794
Provider:
OpenAI
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
“They put the cinnamon rolls in the wrong case again.” “Or someone wanted them closer to the door. Easier to grab and run.” “You think everything’s a theft waiting to happen.” “In this town? It usually is. You heard about Mrs. Talbot’s missing brooch?” “Everyone’s heard about it. She interrogated the choir like we were suspects on a talk show. Maybe she just misplaced it.” “She didn’t misplace it in that display case.” “You can’t be serious. You think the brooch is here? Next to the coconut macaroons?” “Not now. Last Thursday. Look at the lock on the pastry case.” “It’s just old. George refuses to replace anything that still holds sugar.” “The metal’s bright along the edge. Someone forced it recently. Fresh scratch marks.” “Stop leaning over the counter, you’ll smudge the glass. If George comes out of the kitchen, he’ll ban you again.” “He banned me for asking why the register came up short, not for solving crimes.” “You didn’t solve anything, you insulted his math.” “His math was missing forty-two dollars and a sapphire brooch.” “Coincidence.” “Coincidences don’t leave tiny blue stones under the cash drawer.” “…You took the stone?” “I bagged it. Want to help me return a brooch before the morning rush?”
created_at
"2026-02-16T13:11:13.163971+00:00"
2/16/2026, 1:11:13 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5198
moderation_latency
(null)
generation_time
14232
tokens_prompt
81
tokens_completion
486
native_tokens_prompt
67
native_tokens_completion
371
native_tokens_completion_images
0
native_tokens_reasoning
84
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.00379375
router
(null)
provider_responses
0
id
"resp_01f7cf1e75d955220169931762816881959df4266e0e9e4760"
status
200
is_byok
false
latency
141
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771247458-dlLVPwtv01n67zEkdMXj"
upstream_id
"resp_01f7cf1e75d955220169931762816881959df4266e0e9e4760"
total_cost
0.00379375
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)