NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD67FQJQTA8XJ3VB9Z1JE23
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.0s
Cost:
$0.004394
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
99.82%
Dialogue to Total Word Ratio
(details)
99.8695%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 bouncy castle, where a clown was being loudly heckled by seven-year-olds. Bill was stuffing his pockets with balloons, claiming it was camouflage. The plan was simple: sneak in as party entertainers, stuff every present into the piƱata, and walk out whistling. Bill had spent the morning gluing a fake mustache to his chin, which now pointed vaguely left, making him look like a walrus that had given up. Molly wore a fairy costume she refused to explain. They watched the birthday boy tear through wrapping paper like a small, feral badger, and Bill sighed with something close to professional admiration. A bouncy castle deflated mysteriously, and both pretended not to notice the other adjusting their escape route. The cake was enormous, suspiciously so, and Molly suspected the parents were laundering money through buttercream. "The presents are our priority," Molly whispered. "And the cake?" Bill asked. "Fine. The cake too." "You're the best partner ever." "Don't get sentimental in the hedge, Bill." Somewhere inside, a child screamed about a magician. The two thieves nodded at each other, straightened their disguises, and marched toward the patio like heroes of crime.
created_at
"2026-07-25T17:47:36.062Z"
7/25/2026, 5:47:36 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2468
moderation_latency
(null)
generation_time
11898
tokens_prompt
75
tokens_completion
324
native_tokens_prompt
147
native_tokens_completion
290
native_tokens_completion_images
(null)
native_tokens_reasoning
9
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
0.0043941
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64f6a37e31418b01e55190"
is_byok
false
latency
2466
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-1785001656-m0qDbwmrftD0EW1s4DVj"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001656-uRdWZ1776lhPi1dDUkV1"
upstream_id
"chatcmpl-6a64f6a37e31418b01e55190"
total_cost
0.0043941
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
99.92%
Matches word count
n/a
neededClean
false
words
197
99.82%
Dialogue to Total Word Ratio
Ratio: 12.06%, Deviation: 2.06%
neededClean
false
wordsTotal
199
wordsDialogue
24
99.8695%