NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2H7MTTX6667836J485VH3J
Run Details
Model:
DeepSeek V4 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
55.3s
Cost:
$0.001747
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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
“Pass me the blueprints, Bill.” “It’s a napkin with a giraffe on it, Molly.” “And it’s our way in. You see the bouncy castle positioned here?” “I see an inflatable deathtrap surrounded by tiny, screaming apex predators.” “That’s our extraction point. We enter as party clowns.” “Absolutely not. The last time I wore a wig, I got glitter in my eye for a week. I still blink sparkles.” “This is bigger than glitter, Bill. This is little Kaitlyn’s fourth birthday. Her father’s a hedge fund manager. The gift table will be groaning under the weight of platinum-dipped xylophones and trust funds disguised as savings bonds. We’re not stealing presents; we’re reallocating excessive future capital.” “Fine. But I’m not doing balloon animals. I have a moral objection. The squeaking haunts my dreams.” “You’ll be Sorrowful Sam, the mime. Silent. Tragic. Completely unapproachable by children.” “I can do that. How do I make a child weep from a distance of ten feet?” “Just be yourself. Now, the cake-slicing ceremony is our cue. The parents will be a sobbing, Instagramming mess. You’ll execute a slow-motion pratfall to draw any remaining attention, and I’ll shovel the haul into a sack disguised as a sleeping therapy pony.” “And the magician who’s already booked?” “I’ve replaced his rabbit with a furious ferret. The ensuing chaos gives us a seven-minute window.” Bill cracked his knuckles. “A mime and a disaster. It’s almost poetic.”
created_at
"2026-04-25T14:38:50.327Z"
4/25/2026, 2:38:50 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5424
moderation_latency
(null)
generation_time
28756
tokens_prompt
77
tokens_completion
400
native_tokens_prompt
67
native_tokens_completion
365
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"
usage
0.0017467
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
is_byok
false
latency
270
model_permaslug
"deepseek/deepseek-v4-pro-20260423"
provider_name
"DeepSeek"
status
429
1
endpoint_id
"13bda129-f8a6-4a60-b1db-98082e5f7ccd"
id
"ogZiAhk-6z2FuN-9f1e1800a001ed35"
is_byok
false
latency
5424
model_permaslug
"deepseek/deepseek-v4-pro-20260423"
provider_name
"Together"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777127930-QxF6Z2YGhovD0YvUgBns"
session_id
(null)
api_type
"completions"
id
"gen-1777127930-txcN4EBxYsNMv5Sqbzj4"
upstream_id
"ogZiAhk-6z2FuN-9f1e1800a001ed35"
total_cost
0.0017467
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
236
0.00%
Dialogue to Total Word Ratio
Ratio: 98.33%, Deviation: 48.33%
neededClean
false
wordsTotal
240
wordsDialogue
236
0.0000%