NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5X1PNG7GHE1607PK5WWV9
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
14.6s
Cost:
$0.005594
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
27.73%
Dialogue to Total Word Ratio
(details)
47.9155%
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 crouched behind the hedge, binoculars trained on the backyard. Bill crouched beside her, eating a sandwich. "Put that away," she hissed. "We're professionals." "It's pastrami. Professionals eat." "Focus. Sixteen presents on that picnic table. Piñata shaped like a donkey. One clown, possibly armed." "Clowns aren't armed, Molly." "That one's got a balloon sword and dead eyes, Bill." Bill squinted through the fence slats. "The cake says 'Happy 7th Birthday, Tyler.' We're robbing a seven-year-old." "We're liberating merchandise from an over-gifted child. Tyler won't miss a Nerf gun." "He'll miss sixteen Nerf guns." "Details." Molly unrolled a hand-drawn map. "Phase one: you go in dressed as a magician." "Why me?" "Because you own a cape." "It's a Snuggie." "Nobody checks. You perform, distract the parents, I load the presents into the van." "What's my stage name?" "The Great Billdini." "That's terrible." "You have ten seconds to think of a better one." "...Billdini it is." Molly checked her watch. "The piñata breaks at three. That's our window." "And if the clown intervenes?" She pulled a tire iron from her bag. "Then the Great Billdini gets a very educational afternoon." Bill sighed. "I hate birthday jobs." "Everyone hates them. That's why they pay in cake." "...Can I keep the cake?" "If Tyler doesn't cry. Now move."
created_at
"2026-07-25T17:41:54.011Z"
7/25/2026, 5:41:54 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2274
moderation_latency
(null)
generation_time
14339
tokens_prompt
75
tokens_completion
368
native_tokens_prompt
147
native_tokens_completion
370
native_tokens_completion_images
(null)
native_tokens_reasoning
16
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
0.0055941
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64f55010c28a8249f44e5a"
is_byok
false
latency
2272
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-1785001314-27vwtOQjKO6H864Apclp"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001314-EbLVl6x4dVDe5X80vmPW"
upstream_id
"chatcmpl-6a64f55010c28a8249f44e5a"
total_cost
0.0055941
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
68.10%
Matches word count
n/a
neededClean
false
words
214
27.73%
Dialogue to Total Word Ratio
Ratio: 79.36%, Deviation: 10.64%
neededClean
false
wordsTotal
218
wordsDialogue
173
47.9155%