NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KC147SHVX4B4C5M8BAQZR7
Run Details
Model:
DeepSeek V4 Flash 0731 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
28.1s
Cost:
$0.000125
Provider:
OpenInference
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.40%
Dialogue to Total Word Ratio
(details)
99.6906%
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 peeked over the hedge. "Okay, Bill, we've got a ninety-second window when the piñata breaks. That's our cue." Bill wiped his brow. "Molly, we're robbing a five-year-old's birthday party. This feels wrong on a spiritual level." "Wrong? Bill, look at that gift table. That's a Lego Millennium Falcon. Retails at a hundred and fifty. That's not a toy, that's a retirement plan." "But the kids—" "The kids are sugar-crazed chaos gremlins. They won't notice a missing present until they're forty. Now, I've mapped the layout. The mom's on diaper duty in the backyard. The dad's passed out on the bouncy castle. The entrance is through the side gate." Bill pointed. "What about that dog? The one wearing the party hat?" "That's a stuffed poodle. It's a decoration." "It moved." "It's a wind-up toy, Bill. Focus. On my signal, we crawl in, grab the Falcon, snag the gift card basket, and we're out through the hedge." "Gift card basket? That's the low-hanging fruit." "Exactly. And if we're lucky, we'll score a Cocomelon backpack too. Now, go. Slow and low." Bill hesitated. "But what if a kid sees us and cries?" Molly grinned. "Then we run faster. Crying is just speed fuel. Move."
created_at
"2026-09-03T10:11:31.207Z"
9/3/2026, 10:11:31 AM
model
"deepseek/deepseek-v4-flash-20260731"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
578
moderation_latency
(null)
generation_time
28032
tokens_prompt
75
tokens_completion
759
native_tokens_prompt
67
native_tokens_completion
758
native_tokens_completion_images
(null)
native_tokens_reasoning
447
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
0.00012463
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788430291-h8BFB8ahtpaNM7uXCiTA"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788430291-hGobU9L8R7q1Kox5v8Ct"
upstream_id
"chatcmpl-8983c18c-d90c-40a2-a8ce-62e33e40d7e4"
provider_responses
0
endpoint_id
"f954a48e-1c90-433b-9348-4720f8030331"
id
"chatcmpl-8983c18c-d90c-40a2-a8ce-62e33e40d7e4"
is_byok
false
latency
578
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"OpenInference"
status
200
total_cost
0.00012463
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenInference"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
99.40%
Dialogue to Total Word Ratio
Ratio: 92.79%, Deviation: 2.79%
neededClean
false
wordsTotal
208
wordsDialogue
193
99.6906%