NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KC1WSM4K22WQ2AAFMQFHP4
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
34.7s
Cost:
$0.010505
Provider:
Fireworks
Evaluation summary
Score
Evaluator
Details Link
0.21%
Matches word count
(details)
99.88%
Dialogue to Total Word Ratio
(details)
50.0495%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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: "Okay, Bill, walk me through the birthday job." Bill: "Simple. I rent the inflatable T-Rex costume. You pose as the face painter." Molly: "I can't paint faces." Bill: "You can paint fences, walls, occasionally your own elbow. Good enough." Molly: "What's the exit strategy?" Bill: "We load the presents into the bouncy castle and float away." Molly: "That's not how bouncy castles work." Bill: "Not with that attitude." Molly: "Fine. How do we get past the parents?" Bill: "I'll shout 'piƱata emergency' and toss glitter. They'll panic, blind, and bump into each other." Molly: "And the children?" Bill: "I'll tell them the magician is in the garden. They'll stampede." Molly: "There is no magician." Bill: "The birthday clown will have to cope." Molly: "Won't the clown recognize you?" Bill: "No, because I'm not invited. That's the whole point." Molly: "And the cake?" Bill: "We leave the cake. We're thieves, Molly, not monsters." Molly: "So we escape with bags of wrapped toys?" Bill: "Yes. Yours are probably clothes. Mine are probably loud." Molly: "What if we get cornered by a dad?" Bill: "I'll challenge him to a balloon animal duel. No dad can resist." Molly: "You don't know how to make balloon animals." Bill: "Neither does he. That's the beauty." Molly: "Deal. But if I see a toddler with a juice box, I'm out." Bill: "Coward." Molly: "Professional."
created_at
"2026-09-03T10:11:56.353Z"
9/3/2026, 10:11:56 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
598
moderation_latency
(null)
generation_time
34580
tokens_prompt
75
tokens_completion
2324
native_tokens_prompt
146
native_tokens_completion
2604
native_tokens_completion_images
(null)
native_tokens_reasoning
2222
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
0.01050456
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788430316-xy5uGaV9DLOYatsNMu6j"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788430316-Ja3I41j7tjDxitYlZGFe"
upstream_id
"chatcmpl-0b5971e8dd734e3dbb2527d0da288dba"
provider_responses
0
endpoint_id
"ef03a21f-1e70-4f34-9fd9-c6e823f2fcfd"
id
"chatcmpl-0b5971e8dd734e3dbb2527d0da288dba"
is_byok
false
latency
598
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"Fireworks"
status
200
total_cost
0.01050456
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Fireworks"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
0.21%
Matches word count
n/a
neededClean
false
words
228
99.88%
Dialogue to Total Word Ratio
Ratio: 88.16%, Deviation: 1.84%
neededClean
false
wordsTotal
228
wordsDialogue
201
50.0495%