NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD80ZMX8JEZ1XBKQQ3W01Q4
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 21s
Cost:
$0.042899
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.83%
Dialogue to Total Word Ratio
(details)
99.9088%
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 unrolled the blueprint over a casserole dish. “We enter through the bounce house at three, disguised as clowns.” Bill adjusted his red nose. “I look more like a warning than a clown.” “Perfect. Fear buys silence,” Molly said. “And the piñata?” “Decoy. When Jasper swings, we swap the gift table for our replica.” Bill frowned at the crayon map. “Why is the replica drawn in spaghetti?” “Because ink is traceable.” “So is marinara.” Molly sighed. “Fine, we improvise. You juggle. I pocket anything shaped like a toy dinosaur.” “What if a kid sees us?” “Tell them we’re from the Present Police.” “That sounds illegal.” “It is, Bill. That’s the job.” Bill peeked at balloons bobbing like bright hostages. He whispered, “I feel bad.” “Save guilt for after cake.” “Then I’m in.” “Please practice your honk.” Bill honked. Inside, a toddler honked back with terrible confidence. Molly froze beside the cupcake tower. Bill considered the duffel, the door, and his life choices. Then the birthday magician shouted for volunteers. Molly smiled like a felony wearing lipstick. Bill swallowed hard. The children began chanting for a trick. Molly lifted two empty sacks. Bill bowed deeply. Confetti fell like evidence.
created_at
"2026-07-25T18:19:00.132Z"
7/25/2026, 6:19:00 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2261
moderation_latency
(null)
generation_time
80954
tokens_prompt
75
tokens_completion
2789
native_tokens_prompt
147
native_tokens_completion
2857
native_tokens_completion_images
(null)
native_tokens_reasoning
2551
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
0.0428991
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64fe029cb3688ee6e20be1"
is_byok
false
latency
2261
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-1785003540-0nC6KF0wribtFELMTtuL"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785003540-medkrDcTKB7JbN9OSUwW"
upstream_id
"chatcmpl-6a64fe029cb3688ee6e20be1"
total_cost
0.0428991
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
99.98%
Matches word count
n/a
neededClean
false
words
198
99.83%
Dialogue to Total Word Ratio
Ratio: 52.02%, Deviation: 2.02%
neededClean
false
wordsTotal
198
wordsDialogue
103
99.9088%