NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0AK45FSVTYJA1B1T67XB3B
Run Details
Model:
GPT-5.4 Mini
Test:
Tool usage within Novelcrafter
Scenario:
Create alternate prose sections
Duration:
2.7s
Cost:
$0.002135
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"> Near the stables, Frederick was met by Sir Roland, a broad-shouldered knight with a weathered face and a steady gaze. The knight’s polished armor caught the fading light as he gave a curt nod of welcome. “You must be the new squire,” Sir Roland said. “Come, then. If you’re to serve here, you’ll learn quickly that horses and steel both demand respect.” Frederick straightened at once, eager to prove himself, as the smell of hay and leather drifted through the cool evening air. </nc-section> <nc-section data-title="Version 2" data-color="green"> As Frederick approached the stables, a voice called out from beside the rows of tired horses. Sir Roland, the local knight, stepped forward with one hand resting on the pommel of his sword. “So,” he said with a faint smile, “you’re the boy sent to us at last.” Frederick bowed awkwardly, feeling the weight of the knight’s presence. Roland glanced toward the stable hands, then back to Frederick. “You’ll begin by learning the care of mounts,” he said. “A squire who cannot earn a horse’s trust cannot earn a knight’s either.” </nc-section> <nc-section data-title="Version 3" data-color="blue"> The stables lay in shadow when Frederick arrived, but Sir Roland was impossible to miss, standing tall beside the great doors in his knightly surcoat. “Frederick, is it?” he asked, his tone firm but not unkind. “I’ve been told you have a quick mind. Good. You’ll need it here.” He motioned for Frederick to follow him past the stalls, where the horses shifted and stamped softly. “Before you touch a sword,” Sir Roland said, “you’ll learn the language of reins, saddle, and discipline. Come—let us see what sort of squire you truly are.” </nc-section>
created_at
"2026-03-18T11:16:45.885Z"
3/18/2026, 11:16:45 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
688
moderation_latency
(null)
generation_time
2517
tokens_prompt
318
tokens_completion
469
native_tokens_prompt
302
native_tokens_completion
424
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.0021345
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_086c1a4071c0cfda0169ba899dfa68819592f61dd2dcefdab3"
is_byok
false
latency
335
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-1773832605-trF3UfrXJKzL5a4leE7F"
upstream_id
"resp_086c1a4071c0cfda0169ba899dfa68819592f61dd2dcefdab3"
total_cost
0.0021345
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