NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD7NZQX8KEBNEWA88MBC2S3
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
16.8s
Cost:
$0.005954
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
99.92%
Dialogue to Total Word Ratio
(details)
80.0990%
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 unrolled the blueprint across the hood of the car. "Okay, Bill. Target: the Hendersons' backyard. Saturday, two p.m." "A kid's birthday party? Molly, we've hit banks." "Banks don't have a limited edition Turbo Dino action figure, Bill. Little Timmy Henderson does. Now, the clown arrives at two-fifteen—" "Which clown?" "There's only one clown. That's our window. You go in dressed as the balloon artist." "I can't make balloon animals." "Nobody can, Bill. That's the cover. Everyone just nods politely while you mangle a dog." Molly tapped the diagram. "I'll be the cake. I wheel myself in, I pop out at the piñata, and during the chaos, we load the presents into the bouncy castle." "The bouncy castle?" "It has a hidden trapdoor. I modified it last Tuesday. I told Mrs. Henderson I was from the rental company." "She believed you?" "Bill, no one questions a woman holding a clipboard." Molly folded the blueprint. "One rule. Nobody gets hurt, and we do not, under any circumstances, take the birthday boy's actual cake." "What if the cake looks really good?" "Bill." "I'm just saying, we should have a contingency for cake." "Fine. Contingency C is cake. Happy?" "Extremely. Do I get a hat as the balloon guy?" "A tiny one." "This is why we're partners, Molly."
created_at
"2026-07-25T18:12:59.78Z"
7/25/2026, 6:12:59 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2168
moderation_latency
(null)
generation_time
16721
tokens_prompt
75
tokens_completion
404
native_tokens_prompt
147
native_tokens_completion
394
native_tokens_completion_images
(null)
native_tokens_reasoning
67
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
0.0059541
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64fc9be928ed0a0d388000"
is_byok
false
latency
2168
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-1785003179-ai6xPpkfUoczqcsFXnGu"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785003179-SvN9dzpP3RxK49tVEj39"
upstream_id
"chatcmpl-6a64fc9be928ed0a0d388000"
total_cost
0.0059541
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
60.28%
Matches word count
n/a
neededClean
false
words
215
99.92%
Dialogue to Total Word Ratio
Ratio: 91.67%, Deviation: 1.67%
neededClean
false
wordsTotal
216
wordsDialogue
198
80.0990%