NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2H46Y9QP8M5STAQ51QHCYD
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
21.9s
Cost:
$0.000490
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly squinted at the crayon-drawn map on the diner napkin. “So the bouncy castle is the diversion?” Bill nodded, tapping a juice box. “Exactly. I’ll inflate it to catastrophic proportions. The ensuing chaos buries the parents in a tidal wave of screaming, sugared-up toddlers.” “And I waltz through the gift table disguised as the entertainment.” Molly produced a rainbow wig and a kazoo from her satchel. Bill grimaced. “A clown? That’s your masterstroke? Kids hate clowns.” “Kids hate *sad* clowns. I’m a *magic* clown. I pull a live rabbit out of a hat and while they’re mobbing the bunny, I fill the hatchback with Lego and dollhouses.” “The rabbit’s not live, is it?” “It’s a wind-up toy. It just looks real if I scream convincingly.” Bill drummed his fingers. “Fine. But we need a flawless exit. The ice cream truck?” “Melts under pressure. I stole a school bus. We’ll paint ‘Field Trip to Disappointment’ on the side and nobody will follow.” “That’s bleak, even for us.” “Bleak is my brand.” She pocketed the napkin. “Cry on my signal, and don’t skimp on the tears.” “I’ll be weeping before the first gift bag’s gone,” Bill said, adjusting his tiny party hat with grim determination.
created_at
"2026-04-25T14:36:37.359Z"
4/25/2026, 2:36:37 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
975
moderation_latency
(null)
generation_time
16038
tokens_prompt
77
tokens_completion
556
native_tokens_prompt
67
native_tokens_completion
530
native_tokens_completion_images
(null)
native_tokens_reasoning
196
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"
usage
0.000490245
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"2a043438-ceed-447b-b1ba-17fbb3dfc8ec"
is_byok
false
latency
278
model_permaslug
"deepseek/deepseek-v4-pro-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-1777127797-BYSt30Z5Lrg3W8OinaSi"
session_id
(null)
api_type
"completions"
id
"gen-1777127797-WwYXo3zBIXGX2f2y86nv"
upstream_id
"2a043438-ceed-447b-b1ba-17fbb3dfc8ec"
total_cost
0.000490245
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
203
0.00%
Dialogue to Total Word Ratio
Ratio: 76.70%, Deviation: 26.70%
neededClean
false
wordsTotal
206
wordsDialogue
158
49.9595%