NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2J1EEG7ES78NFY6QZPY5W4
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Tool usage within Novelcrafter
Scenario:
Create alternate prose sections
Duration:
8.3s
Cost:
$0.000155
Provider:
DeepSeek
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: Stern Challenge" data-color="red"> I reined Thunder to a halt in the stable yard, the cobblestones ringing beneath his hooves. A broad-shouldered knight in battered steel plate leaned against the stable door, his arms crossed. "So, the whelp arrives," Sir Roland said, his eyes cold as winter steel. He did not offer a hand. Instead, he gestured with his chin toward a bale of hay. "Tend your own horse. Here, a squire earns his keep before he earns a name." The stablemaster scurried aside, and I felt the weight of his gaze—testing, judging, waiting for me to falter. </nc-section> <nc-section data-title="Version 2: Warm Mentor" data-color="green"> As I slid from Thunder’s saddle, a voice boomed with hearty laughter. "By the Dragon’s grace, a new face!" Sir Roland strode forward, his armor polished to a soft gleam, his gauntlets removed to reveal calloused hands. He clapped me on the shoulder, nearly knocking me off balance. "Let me take that burden, lad. I was a squire once, and no horse should suffer a cold stable on a first night." With a wink, he handed me a waterskin and led Thunder toward a warm stall, already whistling a cheerful tune. </nc-section> <nc-section data-title="Version 3: Mysterious Silence" data-color="blue"> The stable yard was empty save for the whisper of hay and the stamp of hooves. Then a shadow detached itself from the wall—Sir Roland, tall and still as a moonlit statue. He said nothing, only studied me with eyes that held the gray of distant storms. After a long pause, he touched his brow in a silent salute, then turned and pointed toward a trough of water for my horse. The gesture was clear: *Follow. Learn. Speak when you have earned the right.* The night air thickened with unspoken portents. </nc-section>
created_at
"2026-04-25T14:52:29.524Z"
4/25/2026, 2:52:29 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
555
moderation_latency
(null)
generation_time
8200
tokens_prompt
318
tokens_completion
557
native_tokens_prompt
291
native_tokens_completion
512
native_tokens_completion_images
(null)
native_tokens_reasoning
81
native_tokens_cached
256
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"
usage
0.000155428
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"6f20ad21-cbe5-4eb1-b3d2-2d767ed9c108"
is_byok
false
latency
283
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepSeek"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777128749-bjOGcR4jPsz78Vj7rwNX"
session_id
(null)
api_type
"completions"
id
"gen-1777128749-vI3yEesEsMGkTD3MRrhq"
upstream_id
"6f20ad21-cbe5-4eb1-b3d2-2d767ed9c108"
total_cost
0.000155428
cache_discount
0.000028672
upstream_inference_cost
0
provider_name
"DeepSeek"
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