NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ099QKHG625A16RTCPGVB5W
Run Details
Model:
MoonshotAI: Kimi K2.6
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4m 24s
Cost:
$0.036645
Provider:
Phala
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
98.8110%
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
"You're telling me we actually gotta case a bouncy house?" Bill asked. Molly checked her clipboard. "Princess theme. Balloon arch at two o'clock, presents stacked by the cake table near the sliding door. Should be an easy grab." "Can't believe professional thieves are boosting Elsa dolls." "Limited edition release. These parents dropped three grand on goodies alone. We're talking drones, mini bikes, and top-shelf gaming consoles." "What about the hired clown?" "Miller's outside doing the big distraction. He's juggling actual fire. Once the kids rush the lawn, we slip through the kitchen and straight into the dining room." "And if some hyperactive brat catches us in the act?" Molly pulled two party hats from her bag. "Then we blend perfectly. Sing happy birthday, eat some cake, walk out with gift bags like proud aunts who just came from the salon." "You've honestly thought of everything." "Always do." She handed him a noisemaker. "Blow this twice if the magician comes back early." "This is deeply humiliating." "It's a professional heist, Bill. Dignity left the building about three hours ago." "Fine. But I'm eating my weight in buttercream cupcakes before we load a single thing into the van." "Deal. Just don't get colorful sprinkles on the leather upholstery, okay?"
created_at
"2026-04-24T17:41:15.006Z"
4/24/2026, 5:41:15 PM
model
"moonshotai/kimi-k2.6-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2631
moderation_latency
(null)
generation_time
253236
tokens_prompt
77
tokens_completion
7267
native_tokens_prompt
69
native_tokens_completion
7950
native_tokens_completion_images
(null)
native_tokens_reasoning
6923
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"
usage
0.03664521
router
(null)
provider_responses
0
endpoint_id
"aa515fc0-facb-44e0-934b-aa0fd1e5e60f"
is_byok
false
latency
10077
model_permaslug
"moonshotai/kimi-k2.6-20260420"
provider_name
"Venice"
status
504
1
endpoint_id
"bb5de010-8234-4abb-b511-025d1817134a"
id
"chatcmpl-8aebacd580cd2b3b"
is_byok
false
latency
2631
model_permaslug
"moonshotai/kimi-k2.6-20260420"
provider_name
"Phala"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777052475-tTBQzAFYJA8kBZxttQFH"
session_id
(null)
api_type
"completions"
id
"gen-1777052475-3XHXVNdeRCy0m1EnvX1U"
upstream_id
"chatcmpl-8aebacd580cd2b3b"
total_cost
0.03664521
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Phala"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
207
99.99%
Dialogue to Total Word Ratio
Ratio: 90.87%, Deviation: 0.87%
neededClean
false
wordsTotal
208
wordsDialogue
189
98.8110%