NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1J7YV5X1N3R5XR1MTJ0P4A
Run Details
Model:
MiniMax M3
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
29.2s
Cost:
$0.000514
Provider:
Minimax
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
40.0831%
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 ready for the Morrison job?" "Bill, it's a six-year-old's birthday party." "Exactly. Low security. High reward. The presents alone could fetch us a hundred bucks." "Bill. We're stealing from children." "Relax, we just borrow. Okay, we steal. But think of the toys! Vintage Beanie Babies, Molly. I hear this kid's loaded." "Loaded? His parents bought a piñata from Costco." "Which means premium confetti. That's a five-dollar resale, minimum." "You've lost your mind." "Molly. I've found my calling. Now, I go in as the clown. You—" "I'm not dressing as a clown." "Fine. You be the magician's assistant. You distract the parents, I grab the gift table, we vanish like—" "Into what? A minivan?" "A very fast minivan. I've got it timed. The cake comes out at two-fifteen. Everyone sings. Chaos. We move." "And when the kids cry?" "Kids always cry, Molly. That's not on us." "I'm not sure that's legally accurate." "Since when do we care about legally accurate?" "I care when it involves traumatized toddlers, Bill!" "Fine. We leave the Barbie Dreamhouse." "You'd leave the Dreamhouse?" "It clashes with my aesthetic."
created_at
"2026-06-01T12:23:53.962Z"
6/1/2026, 12:23:53 PM
model
"minimax/minimax-m3-20260531"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1861
moderation_latency
(null)
generation_time
29154
tokens_prompt
77
tokens_completion
493
native_tokens_prompt
236
native_tokens_completion
414
native_tokens_completion_images
(null)
native_tokens_reasoning
176
native_tokens_cached
222
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
0.00051432
router
(null)
provider_responses
0
endpoint_id
"6851b352-a7e2-45ad-a69e-67ed1208a416"
id
"066cacd9f36f3291ada8e06f65b0e58e"
is_byok
false
latency
1861
model_permaslug
"minimax/minimax-m3-20260531"
provider_name
"Minimax"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer
(null)
request_id
"req-1780316633-Q3MzQael9yF43WZHkWGU"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780316633-tQ6QN1qiNOpxxQGCkiLd"
upstream_id
"066cacd9f36f3291ada8e06f65b0e58e"
total_cost
0.00051432
cache_discount
0.00010656
upstream_inference_cost
0
provider_name
"Minimax"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
43.38%
Matches word count
n/a
neededClean
false
words
183
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
187
wordsDialogue
187
40.0831%