NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD4PR8XP0MVBGAXWKESX2ES
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
53.7s
Cost:
$0.025326
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3940%
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, remind me why we're robbing a birthday party." "Because, Bill, rich parents panic-buy ridiculously expensive presents." "So we sneak past the clown, grab the gifts, and leave before cake?" "Exactly. In through the garden, out before the magician produces evidence." "What if a kid sees us?" "Smile, say you're the present inspector, then run like moral bankruptcy." "And the piƱata?" "Decoy. Whack it, shout 'surprise tax audit,' vanish with the bicycles." "Bill, that's deeply unkind." "Molly, we once stole a sandwich from a mime; we have no floor." "Fine, but no puppy this time." "You still miss that puppy." "He barked in Morse code, Bill. He exposed us." "Focus. Balloons mean cameras, clowns mean chaos, grandma means getaway driver." "Grandma agreed?" "She thinks we're collecting donations for brave little orphans." "We are the orphans, technically." "Spiritually, absolutely. Now lace your squeaky shoes." "Why squeaky?" "So if we get caught, everyone assumes we're part of the show." "Genius." "Or doomed." "Same thing at children's parties. Ready?" "No. Mask on anyway?" "Obviously. Today we steal joy, tomorrow we return receipts." "Bill?" "Fine, we keep joy and donate wrapping paper." "Compromise accepted. To crime!" "To extremely minor, mostly harmless crime!" "For snacks."
created_at
"2026-07-25T17:20:59.173Z"
7/25/2026, 5:20:59 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2210
moderation_latency
(null)
generation_time
53564
tokens_prompt
75
tokens_completion
1607
native_tokens_prompt
147
native_tokens_completion
1659
native_tokens_completion_images
(null)
native_tokens_reasoning
1336
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
0.025326
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64f07b406b1b489a309273"
is_byok
false
latency
2210
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-1785000059-1uM47eJakAlvL088SqKa"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000059-YWhwM9vkvctPD56YuS8C"
upstream_id
"chatcmpl-6a64f07b406b1b489a309273"
total_cost
0.025326
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
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
201
wordsDialogue
201
68.3940%