NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM1GDFY3RR71ME8JBXR03HBZ
Run Details
Model:
MiniMax M2.7
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2m 26s
Cost:
$0.010355
Provider:
Minimax
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
23.13%
Dialogue to Total Word Ratio
(details)
61.5643%
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
Molly and Bill crouched behind a stack of inflatable castles, their breath fogging in the cool morning air. The party’s bright banner flapped overhead, promising games, cake, and a mountain of presents that glittered like tiny loot. Bill consulted a crumpled map of the backyard, his finger tracing a secret route through the bounce house. Molly: 'Okay, here's the plan. We slip in during the clown's finale, grab the presents, and vanish before the cake is cut.' Bill: 'Nice, but the DJ's speakers are louder than a marching band. We need a distraction, maybe a fake balloon pop.' Molly unfolded a tiny walkie‑talkie, its antenna flickering like a firefly. Molly: 'Ready when you are. I'll handle the cake slice, you snag the loot.' Bill whispered, his voice muffled by a distant squeal of a child on a pony ride. Bill: 'Copy that. If anyone asks, we are the entertainment crew.' Molly grinned, tapping her watch as an inflatable dinosaur loomed behind them, its grin too wide for comfort. Molly: 'If the clown sneezes, we’re done. I’ll have a backup snack bag to throw the kids off, and you’ll slip the glitter bomb under the tablecloth for safety and watch now.'
created_at
"2026-03-18T22:17:47.212Z"
3/18/2026, 10:17:47 PM
model
"minimax/minimax-m2.7-20260318"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1370
moderation_latency
(null)
generation_time
145742
tokens_prompt
77
tokens_completion
8375
native_tokens_prompt
101
native_tokens_completion
8604
native_tokens_completion_images
(null)
native_tokens_reasoning
8339
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0103551
router
(null)
provider_responses
0
endpoint_id
"471cf4ea-3548-4dd7-9f86-8c0f9c21d3ca"
id
"060a578b67a91051e349c430ba1f7817"
is_byok
false
latency
1368
model_permaslug
"minimax/minimax-m2.7-20260318"
provider_name
"Minimax"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773872267-pkg8ksd6YQoB1hRr9Gbp"
upstream_id
"060a578b67a91051e349c430ba1f7817"
total_cost
0.0103551
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Minimax"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
23.13%
Dialogue to Total Word Ratio
Ratio: 39.00%, Deviation: 11.00%
neededClean
false
wordsTotal
200
wordsDialogue
78
61.5643%