NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5Z64ZXX9KJCNBB9M8AGXP
Run Details
Model:
DeepSeek V3.2
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 24s
Cost:
$0.000150
Provider:
Phala
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 peered through the binoculars. “Okay. The inflatable dragon is the centerpiece. Presents are stacked by the picnic table, near the cake.” Bill adjusted his fake mustache, unnecessary for their current rooftop vantage point. “Right. Operation Sugar Rush is a go. Distraction?” “You,” Molly said, without lowering the lenses. “You’ll be the disgruntled clown they hired but got the date wrong. Start a scene about missing balloons. Loudly.” “I hate clowns,” Bill grumbled, fiddling with the rainbow suspenders of his costume. “We all have our crosses to bear. Once the adults are distracted, I slip in as the cheerful, efficient party planner they definitely *did* hire. I’ll consolidate the loot into a gift bag marked ‘Party Supplies’.” “What about the kids? They’re observant little gremlins.” Molly finally looked at him, a grin spreading. “The piñata. I’ll bring a backup. It’ll be full of extra-strength sugar cubes. They’ll be vibrating into next Tuesday.” Bill nodded slowly, a flicker of professional admiration in his eyes. “Clean. But the timeline’s tight. The magician arrives at three.” “Then stop complaining and go put your big red nose on. Remember, the goal is the new Super Robo-Falcon 9000s. I hear they’re under every third tree this season.” “A humanitarian crisis,” Bill said solemnly, heading for the ladder. “We’re practically doing a public service.”
created_at
"2026-02-16T21:35:05.875593+00:00"
2/16/2026, 9:35:05 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1763
moderation_latency
(null)
generation_time
83954
tokens_prompt
77
tokens_completion
388
native_tokens_prompt
66
native_tokens_completion
331
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00015022
router
(null)
provider_responses
0
id
"dfa0de1b0b66462aa4da74865f2e99e0"
status
200
is_byok
false
latency
1763
endpoint_id
"4e9fb7e9-3967-4cd4-9723-df614f9f228e"
provider_name
"Phala"
model_permaslug
"deepseek/deepseek-v3.2-20251201"
api_type
"completions"
id
"gen-1771277621-ywaCrFoMBXMBiLTHcGRb"
upstream_id
"dfa0de1b0b66462aa4da74865f2e99e0"
total_cost
0.00015022
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Phala"
Evaluation details
Result
Evaluator
Details
Meta Data
27.1658%
Matches word count
n/a
neededClean
false
words
219
0.0000%
Dialogue to Total Word Ratio
Ratio: 73.06%, Deviation: 23.06%
neededClean
false
wordsTotal
219
wordsDialogue
160
13.5829%