NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1HVCM18CZZWVCAJR85MPF8
Run Details
Model:
MiniMax M3
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
22.7s
Cost:
$0.000472
Provider:
Minimax
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
99.34%
Dialogue to Total Word Ratio
(details)
98.4817%
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
"Don't we look fabulous," Bill whispered, adjusting his party hat. "Like two people who definitely belong at a six-year-old's birthday." "Better question," Molly said, peering around the hedge. "Do we look like we brought gifts? Because I draw the line at shopping." "You brought a weapon?" "I brought a gift bag. Empty." "Genius." Bill snickered. "So what's the plan, oh mastermind of kindergarten crime?" "We mingle. We befriend the birthday brat. We wait for cake." "Then?" "Then everyone goes into sugar shock, and we raid the present table like our lives depend on it. Which they might. You owe Marco three thousand dollars, Bill." "I hate when you bring up Marco during heist briefings." "Focus. What's our exit strategy?" "Window above the bouncy castle." "Bill, that's a twelve-foot drop onto a children's inflatable." "I once survived worse in Prague." "You broke your ankle in Prague." "Ankles heal. Marco's collection agency does not." "Fine. I distract the clown. You grab the loot." "What if the clown suspects?" "Bill, you are a grown man in a bow tie. The clown is the least of our worries." "Touché. Let's go steal from toddlers, Moll." "For Marco."
created_at
"2026-06-01T12:17:02.087Z"
6/1/2026, 12:17:02 PM
model
"minimax/minimax-m3-20260531"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1497
moderation_latency
(null)
generation_time
22669
tokens_prompt
77
tokens_completion
431
native_tokens_prompt
236
native_tokens_completion
357
native_tokens_completion_images
(null)
native_tokens_reasoning
105
native_tokens_cached
114
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
0.00047184
router
(null)
provider_responses
0
endpoint_id
"6851b352-a7e2-45ad-a69e-67ed1208a416"
id
"066cab3edd5e48aceefea2ab2a9f21be"
is_byok
false
latency
1493
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-1780316222-x9xEgDoPAxNbFPSNtJi4"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780316222-ygVkB2iqy81rEa80IA2u"
upstream_id
"066cab3edd5e48aceefea2ab2a9f21be"
total_cost
0.00047184
cache_discount
0.00005472
upstream_inference_cost
0
provider_name
"Minimax"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
193
99.34%
Dialogue to Total Word Ratio
Ratio: 92.86%, Deviation: 2.86%
neededClean
false
wordsTotal
196
wordsDialogue
182
98.4817%