NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD6AZG3SAPZPTVA26CX8VQ4
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
23.4s
Cost:
$0.010109
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
69.03%
Dialogue to Total Word Ratio
(details)
44.6119%
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
"We're robbing a five-year-old's birthday party," Bill said. "Not robbing," Molly said. "Liberating the presents." "They're children, Molly." "Children who own a PlayStation 5, Bill. Children who haven't suffered." "You've lost your mind." "I've found our retirement. Little Timmy's gift table has three iPads and a drone." "A drone?" "A drone. Now, the plan. You go in dressed as a clown." "Why am I the clown?" "Because you cried at the puppet show last Tuesday." "It was a moving performance!" "Exactly. Wasted on crime. Meanwhile, I'll be the balloon artist." "You can't make balloon animals." "I can make a balloon snake." "That's just a balloon." "Details, Bill. While I distract them with snakes, you load the presents into the bouncy castle." "And then?" "Then we bounce it down the hill to the getaway van." "That's insane." "It's aerodynamic." "It's inflatable!" "Same thing, probably. Oh, and grab the cake." "Molly, we're not stealing the cake." "It has my name on it." "It says 'Happy Birthday Timmy.'" "Close enough. Synchronize watches." "I don't have a watch." "Then synchronize vibes, Bill. We're professionals."
created_at
"2026-07-25T17:49:30.505Z"
7/25/2026, 5:49:30 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2228
moderation_latency
(null)
generation_time
23366
tokens_prompt
75
tokens_completion
727
native_tokens_prompt
147
native_tokens_completion
671
native_tokens_completion_images
(null)
native_tokens_reasoning
382
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
0.0101091
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64f72ba62884957d818333"
is_byok
false
latency
2228
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-1785001770-W5dYeKuBpH55tL9dXRot"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001770-E4KgECLLw5ahBEJJgmHb"
upstream_id
"chatcmpl-6a64f72ba62884957d818333"
total_cost
0.0101091
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
20.19%
Matches word count
n/a
neededClean
false
words
180
69.03%
Dialogue to Total Word Ratio
Ratio: 97.80%, Deviation: 7.80%
neededClean
false
wordsTotal
182
wordsDialogue
178
44.6119%