NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD74E1NW7Z4BNSRTE0W9CQ2
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
12.3s
Cost:
$0.005084
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
50.0000%
Overall
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 spread the blueprint across the dashboard, squinting in the glow of Bill's flashlight. "Okay. The piñata hangs here. The bouncy castle covers the east exit." "Tell me again why we're robbing a seven-year-old," Bill said. "Because little Jayden's grandmother is rich, and rich grandmothers buy gold-plated tricycles." "That's not a thing." "It is now. Focus." She tapped the map. "You go in dressed as the clown." "I get hives from face paint." "You get hives from responsibility. Wear the wig." Bill sighed. "And if the kids catch us?" "Kids are terrible witnesses. Half of them can't count past ten." "Jayden's in gifted math." "Then bribe him with cake." Molly rolled up the blueprint and checked her watch. "Cake cutting is at two. That's our window. Chaos, tears, frosting everywhere—nobody notices two clowns carrying thirty gift bags." "One clown," Bill corrected. "You said you're the balloon artist." "Fine. One clown, one balloon artist, thirty gift bags." "What if there's a magician?" Molly paused. "Why would there be a magician?" "There's always a magician, Molly. They see everything. It's literally their job." "Then we take the magician too." "We are not kidnapping a magician." "Desperate times, Bill. Desperate, festive times."
created_at
"2026-07-25T18:03:24.603Z"
7/25/2026, 6:03:24 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2110
moderation_latency
(null)
generation_time
12274
tokens_prompt
75
tokens_completion
342
native_tokens_prompt
147
native_tokens_completion
336
native_tokens_completion_images
(null)
native_tokens_reasoning
18
native_tokens_cached
147
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
0.0050841
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64fa6d6266616237080bb3"
is_byok
false
latency
2110
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-1785002604-PTZ91ryJHc2rrWtyMZJb"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785002604-2wmZJrbc9KctWtVeRtS7"
upstream_id
"chatcmpl-6a64fa6d6266616237080bb3"
total_cost
0.0050841
cache_discount
0.0003969
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
0.00%
Dialogue to Total Word Ratio
Ratio: 82.76%, Deviation: 32.76%
neededClean
false
wordsTotal
203
wordsDialogue
168
50.0000%