NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ04ESPH7KXMKTSFBFG3EVT5
Run Details
Model:
MoonshotAI: Kimi K2.6
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
3m 12s
Cost:
$0.028292
Provider:
Phala
Evaluation summary
Score
Evaluator
Details Link
100.00%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
The bell above the door chimed as flour dust motes danced in the morning sun. Yeast and vanilla lingered in the warm air, mixing with the sharp scent of espresso from the corner machine. Behind the display case, cherry scones cooled beside rows of lemon bars, the glass still smudged from yesterday’s rush. A tray of cinnamon rolls steamed gently on the steel counter, their glaze catching the morning light. "You’re here early." "Couldn’t sleep. The cinnamon rolls called to me." "They don’t start talking until dawn. Trust me, I’ve listened." "Maybe I heard them rehearsing. Or maybe I needed an alibi." "An alibi? At six in the morning in a bakery?" "Someone tampered with the contest entries last night. All the blueberry pie registration forms vanished from the community center." "I heard. Tragic." "You don’t seem surprised." "I’m a baker. Nothing shocks me after midnight." "Were you here after midnight?" "Slow down, detective. I was kneading sourdough and listening to true crime podcasts. Entirely alone." "Convenient." "Delicious, actually. Try the cherry scone. It’s far less suspicious than your line of questioning." "Maybe I’ll take two. One for evidence." "Evidence goes stale." "Not if I bag it properly."
created_at
"2026-04-24T16:16:38.108Z"
4/24/2026, 4:16:38 PM
model
"moonshotai/kimi-k2.6-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1798
moderation_latency
(null)
generation_time
191923
tokens_prompt
81
tokens_completion
5483
native_tokens_prompt
69
native_tokens_completion
6134
native_tokens_completion_images
(null)
native_tokens_reasoning
5142
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
0.02829161
router
(null)
provider_responses
0
endpoint_id
"bb5de010-8234-4abb-b511-025d1817134a"
id
"chatcmpl-bee2360a9511432c"
is_byok
false
latency
1798
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-1777047398-KjkZfN66Rsw3Z4prn9eB"
session_id
(null)
api_type
"completions"
id
"gen-1777047398-8wNm8YhXUY5UvpH256Em"
upstream_id
"chatcmpl-bee2360a9511432c"
total_cost
0.02829161
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Phala"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)