NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8YVK2T4X3YT1ZYXP0BDRKJ
Run Details
Model:
Gemma 4 31B
Test:
Tool usage within Novelcrafter
Scenario:
Create alternate prose sections
Duration:
17.2s
Cost:
$0.000212
Provider:
DeepInfra
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: The Stern Mentor" data-color="red"> As I brought Thunder to a halting stop near the stables, a man stood waiting for me. He was clad in polished steel that mirrored the dying sunlight, his face a map of scars and weathered determination. This was Sir Roland. He didn't smile; instead, he appraised me with a cold, calculating gaze that seemed to weigh my very soul. "You're late, boy," he barked, his voice like grinding stones. "In this castle, a second's delay is the difference between a victory and a casket. Dismount. Now." </nc-section> <nc-section data-title="Version 2: The Jovial Veteran" data-color="green"> I had barely stepped off my horse when a booming laugh echoed through the stable yard. A broad-shouldered knight with a magnificent, salt-and-pepper beard stepped forward, clapping a heavy hand on my shoulder that nearly knocked the wind out of me. "So, you're the new lad!" Sir Roland beamed, his eyes twinkling with genuine amusement. "I've heard you've got spirit, Frederick. Come, let's get your gear sorted before the cook finishes the stew—it's the only thing in this fortress that doesn't taste like old boot leather." </nc-section> <nc-section data-title="Version 3: The Solemn Guardian" data-color="blue"> Near the scent of hay and leather, a figure emerged from the shadows of the stable eaves. Sir Roland approached with a measured, graceful stride, his cape trailing softly behind him. He stopped a few paces away and inclined his head in a slow, dignified nod. "Welcome, Frederick," he said, his voice quiet but carrying a weight of immense authority. "You enter these walls at a time of great uncertainty. The path of a squire is paved with hardship, but if you possess the courage to endure, I shall teach you the secrets of the blade and the honor of the shield." </nc-section>
created_at
"2026-05-10T12:47:37.57Z"
5/10/2026, 12:47:37 PM
model
"google/gemma-4-31b-it-20260402"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
248
moderation_latency
(null)
generation_time
17136
tokens_prompt
318
tokens_completion
471
native_tokens_prompt
329
native_tokens_completion
446
native_tokens_completion_images
(null)
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
"stop"
service_tier
(null)
usage
0.00021225
router
(null)
provider_responses
0
endpoint_id
"4149ab03-3b69-45a0-b94c-6c253b8641a1"
id
"chatcmpl-RRmcaYYq7Zf4ivVi2FCiPfex"
is_byok
false
latency
45
model_permaslug
"google/gemma-4-31b-it-20260402"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778417257-DWzd0JAzYi8AwTlvxPgB"
session_id
(null)
api_type
"completions"
id
"gen-1778417257-1J6d6nTAW4JFxZMBZ38C"
upstream_id
"chatcmpl-RRmcaYYq7Zf4ivVi2FCiPfex"
total_cost
0.00021225
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
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