NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD4PCW11Q0HVBE313Y4D3YN
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
44.2s
Cost:
$0.019026
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
73.94%
Dialogue to Total Word Ratio
(details)
86.9681%
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 spread the invitation across Bill’s dashboard like a treasure map drawn by a sugar-drunk raccoon. Outside, the Hendersons’ lawn glittered with fairy lights, a bouncy castle wheezing like an asthmatic dragon. Bill adjusted his suspiciously cheerful suspenders. “We blend in as clowns,” Molly said. Bill whispered, “I brought balloons and moral flexibility.” Their plan was elegant in the way a falling piano is elegant: enter during the puppet show, admire the gift table, then exit with ninja discretion and possibly a juice box. “Presents first, cake later,” she said. Bill nodded solemnly, then got his shoe stuck in the mail slot while rehearsing his innocent wave. A balloon popped; somewhere, a toddler booed. Molly reconsidered every life choice except the getaway tricycle, which had streamers and excellent torque. “If anyone asks, we’re Uncle Noodles.” Bill saluted with a rubber chicken. The backyard erupted into happy chaos—piñata thunder, kazoo sirens, frosting fog. Molly smiled despite herself. Crime was wrong, but tiny wrapped boxes did have excellent comedic timing. They waited for the magician’s final flourish, when all eyes turned toward the disappearing rabbit and nobody watched the loot. Bill inhaled. Molly cracked her knuckles. Showtime wore a party hat.
created_at
"2026-07-25T17:20:47.498Z"
7/25/2026, 5:20:47 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2688
moderation_latency
(null)
generation_time
44111
tokens_prompt
75
tokens_completion
1276
native_tokens_prompt
147
native_tokens_completion
1239
native_tokens_completion_images
(null)
native_tokens_reasoning
944
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
0.019026
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64f05e57c78a5529a93ec1"
is_byok
false
latency
2688
model_permaslug
"moonshotai/kimi-k3-20260715"
provider_name
"Moonshot AI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1785000047-xHyPoOdfYazowZBS2Y6L"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000047-kFo8OtZDJNeVyEEFunta"
upstream_id
"chatcmpl-6a64f05e57c78a5529a93ec1"
total_cost
0.019026
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Moonshot AI"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
73.94%
Dialogue to Total Word Ratio
Ratio: 17.41%, Deviation: 7.41%
neededClean
false
wordsTotal
201
wordsDialogue
35
86.9681%