NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07KZR8KJDQK5XAYHDSHYB5
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Tool usage within Novelcrafter
Scenario:
Create alternate prose sections
Duration:
3.2s
Cost:
$0.002756
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
Pass
Match blue prose section
(details)
Pass
Match green prose section
(details)
Pass
Match red prose section
(details)
no eval
Overall
Model input
System
You are an expert fantasy novel author. You are working on a novel called "The Chronicles of the Last Dragon". The following tools are available to you: - <nc-section> Use this tool to create a new section of prose. Arguments: - "data-title": The title of the section. - "data-color": Any color of (red, green, blue, yellow, purple, orange, pink, brown). Example usage: <nc-section data-title="Chapter 1: The Arrival" data-color="blue"> Frederick, a young squire, arrives at the castle to begin his training. </nc-section>
User/Human
The story so far: <storySoFar> Frederick, a young squire, arrives at the castle to begin his training. </storySoFar>
AI
My horse, a majestic stallion named Thunder, galloped across the open field. The wind whipped through my hair as I rode towards the castle gates. The sun was setting, casting a warm glow over the stone walls. I could see the banners of the kingdom fluttering in the breeze.
User/Human
Continue the story with the following instructions: """The local knight, Sir Roland, greets Frederick near the stables.""" Create 3 alternate prose sections that continue the story. - Version 1 (red) - Version 2 (green) - Version 3 (blue)
Model response
Messages
Meta
AI
<nc-section data-title="Version 1" data-color="red"> Frederick had barely dismounted when a stern voice called out from beside the stables. “Would you care to let that horse breathe before you flatter it with your staring?” Sir Roland asked, stepping into view with a grin beneath his helmet. Frederick straightened at once. “Forgive me, sir. I’m Frederick, sent here for training.” “Then you’ve come to the right place,” Roland said, clapping him on the shoulder. “A squire learns quickly here—or not at all. Come, we’ll see if you know a bridle from a battle cry.” </nc-section> <nc-section data-title="Version 2" data-color="green"> Near the stables, Frederick was just untacking his horse when a tall knight in polished mail approached, his expression sharp but not unkind. “You must be the new squire,” Sir Roland said. “The stableboys told me to expect a boy with more dust on him than dignity.” Frederick flushed. “I meant no trouble, my lord.” “Trouble is useful if it teaches you something,” Roland replied. He glanced at the horse, then back to Frederick. “Feed him first. Then meet me in the yard. We begin with lessons your master should have already given you.” </nc-section> <nc-section data-title="Version 3" data-color="blue"> The smell of hay and leather filled the air as Frederick led his horse toward the stable doors. There, leaning against a post, stood Sir Roland, his arms folded and his gaze measuring. “So,” Roland said, “you’re the squire they’ve sent me. You look younger than the last one.” Frederick swallowed. “I’ll work hard, sir.” A faint smile touched Roland’s mouth. “Good. Hard work matters more than age. Leave your horse with the stablemaster, Frederick. If you survive your first week, I may even teach you how to hold a sword without looking like you’re wrestling a fish.” </nc-section>
created_at
"2026-03-18T10:24:48.403Z"
3/18/2026, 10:24:48 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
988
moderation_latency
(null)
generation_time
3083
tokens_prompt
318
tokens_completion
507
native_tokens_prompt
302
native_tokens_completion
562
native_tokens_completion_images
0
native_tokens_reasoning
119
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
0.0027555
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_08d7f604a849db8a0169ba7d7074ac8196992da566908aa9e6"
is_byok
false
latency
173
model_permaslug
"openai/gpt-5.4-mini-20260317"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773829488-jGgFAQQH8wLyqqJ8FBQz"
upstream_id
"resp_08d7f604a849db8a0169ba7d7074ac8196992da566908aa9e6"
total_cost
0.0027555
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
Pass
Match blue prose section
/<nc-section data-title="[^"]*" data-color="blue">[^<]+<\/nc-section>/
n/a
Pass
Match green prose section
/<nc-section data-title="[^"]*" data-color="green">[^<]+<\/nc-section>/
n/a
Pass
Match red prose section
/<nc-section data-title="[^"]*" data-color="red">[^<]+<\/nc-section>/
n/a
no eval