NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-20-01M5C6PV7VG8PDRFEQAXK1HV3K
Run Details
Model:
DeepSeek V4.1 Flash 1017 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
19.1s
Cost:
$0.001381
Provider:
Wafer
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 unfolded the party map across the getaway tricycle and tapped the bouncy castle with a crayon. Bill studied the snack table, the piñata, and the suspiciously serene mothers clustered by the punch bowl. The plan required stealth, timing, and an absolute indifference to the moral implications of looting a six-year-old’s birthday. Molly explained the approach: enter as entertainers, distract the horde with balloon animals, then sweep the gift table into a wheeled unicorn hamper while the magician’s rabbit escaped. Bill objected to the costume. “Balloons are the perimeter. We go in as clowns.” “I’m not wearing those shoes.” “And tights.” “Fine, magician.” “No capes.” He practiced sawing a lady in half with a breadstick while Molly installed a glitter smoke bomb in the boombox. The real obstacle, she noted, was the party host’s vigilance, the toddler with a foam sword, and the gluten-free cake table. Bill suggested a diversion: an interpretive dance about sharing. Molly added a contingency for cake. They synchronized watches, which were plastic and made party noises. Then, as the first chorus of Happy Birthday drifted through the fence, they waddled with alarming enthusiasm toward the gate beneath a rainbow, deeply committed and only slightly ashamed.
created_at
"2026-10-20T08:26:37.698Z"
10/20/2026, 8:26:37 AM
model
"deepseek/deepseek-v4.1-flash-20261017"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
351
moderation_latency
(null)
generation_time
19049
tokens_prompt
75
tokens_completion
2749
native_tokens_prompt
93
native_tokens_completion
2732
native_tokens_completion_images
(null)
native_tokens_reasoning
2414
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
0.00138088
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1792484797-L1bS6b1YOK2DFJFaaFKj"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1792484797-Fy1kt1beohYGas87kOiM"
upstream_id
"chatcmpl-17c2506af389442bbe04369b99ec47ca"
provider_responses
0
endpoint_id
"66d4851d-7738-4948-9d40-2ab6dc54f895"
id
"chatcmpl-17c2506af389442bbe04369b99ec47ca"
is_byok
false
latency
351
model_permaslug
"deepseek/deepseek-v4.1-flash-20261017"
provider_name
"Wafer"
status
200
total_cost
0.00138088
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Wafer"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 9.85%, Deviation: 0.15%
neededClean
false
wordsTotal
203
wordsDialogue
20
100.0000%