NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1HVXFV0HJK35X8TKJMB0YM
Run Details
Model:
MiniMax M3
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
4m 6s
Cost:
$0.013914
Provider:
Minimax
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9595%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Get ready, Bill. We're about to make history. Molly adjusted her oversized novelty sunglasses and spread a tattered blueprint across the hood of their getaway car, suspiciously covered in clown decals. Bill was busy inflating a balloon poodle, his hands trembling. The sun beat down on their cul-de-sac headquarters, where a half-eaten birthday cake sat forgotten. She grinned at her partner, who looked less like a master criminal and more like a tired accountant. Today, they would finally pull off the legendary Cake Bandit. "Alright Bill, listen up." She tapped the paper. "The Cake Bandit strikes at three PM. Distracted parents, sugar-high rugrats everywhere. Total chaos. Our kind of chaos." "Are we sure about this?" Bill squeaked. "There'll be... children." "Children with presents, Bill. Forty of them. Forty goodie bags of loot, minimum." "But they'll cry." "They always cry. That's why we bring the squeaky shoes. Tiny brains can't process a squeaky shoe and a missing gift at the same time, Bill." Bill sighed, his balloon poodle drooping sadly. "Fine. But I'm wearing the mustache." "You always wear the mustache." "It boosts my moral ambiguity." "Get in the clown car, Bill. We have a heist to commit."
created_at
"2026-06-01T12:17:19.36Z"
6/1/2026, 12:17:19 PM
model
"minimax/minimax-m3-20260531"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2727
moderation_latency
(null)
generation_time
245547
tokens_prompt
77
tokens_completion
10332
native_tokens_prompt
236
native_tokens_completion
11580
native_tokens_completion_images
(null)
native_tokens_reasoning
10012
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
0.01391352
router
(null)
provider_responses
0
endpoint_id
"6851b352-a7e2-45ad-a69e-67ed1208a416"
id
"066cab4feb67453218af768acf0bbc28"
is_byok
false
latency
2727
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-1780316239-dTJ92DJ3iUYYnx8mTo4i"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780316239-eXujWo6Ebf6dA8ameAmC"
upstream_id
"066cab4feb67453218af768acf0bbc28"
total_cost
0.01391352
cache_discount
0.00010656
upstream_inference_cost
0
provider_name
"Minimax"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
100.00%
Dialogue to Total Word Ratio
Ratio: 50.25%, Deviation: 0.25%
neededClean
false
wordsTotal
201
wordsDialogue
101
99.9595%