NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHNF15QXK8PZEDY7HRK1JT2H
Run Details
Model:
Minimax M2.5
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
5m 13s
Cost:
$0.020882
Provider:
Minimax
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.01%
Dialogue to Total Word Ratio
(details)
50.0028%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 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 hunched over a worn map of the neighborhood, her eyes glittering with mischief. The house on Maple Street was a pastel nightmare of balloons and streamers, but behind the garish façade lay a treasure trove of brightly wrapped presents. She tapped the spot marked with a cartoon clown. Molly: "Alright, Bill, here's the plan. We slip in during the piñata distraction." Bill: "You really think a bunch of eight‑year‑olds will be that distracted by a donkey made of papier‑mâché?" Molly: "Trust me, the sugar high will do the rest." Bill: "Okay, but what about the loot? The presents are stacked like a birthday tower." Molly: "We grab the lot, dump them in the back of my grandma’s shopping cart, and roll out before the cake even hits the table." Bill: "Sounds like a plan, but we need a signal. I don’t want to get caught singing 'Happy Birthday' to a bunch of kids." Molly: "I'll wave a glowing frisbee. When I throw it, that’s our cue." Bill: "Perfect. And if anyone asks, we’re clowns hired for the entertainment." Molly: "Now, let's synchronize our watches. We go in at 3:15, right when the magic show starts." Bill: "Got it. And if the magician pulls a rabbit out of the hat, we’ll steal that too." Molly: "Only if it’s a plush one. I’ve got a soft spot for cuddly loot." Bill: "Deal. Now, let’s move. The cake isn’t going to cut itself." Molly: Remember, how cute the kids look, we don’t steal the balloons. They’re air, not profit. Bill: Right, balloons are distraction, not a dividend. We focus on the presents, not floaters. Molly: And if the birthday song starts, we hum along. It’ll keep us undercover. Bill: Exactly. Just don’t forget to smile. It’s a children’s party, after all. At 3:15, the living room erupted in a burst of glittering confetti as the magician tugged a silk scarf from his sleeve. Molly slipped through the side door, her oversized clown shoes squeaking on the polished floor. Bill trailed behind, shouldering a battered backpack that thudded with each step, more like a marching band than a thief. The piñata, a bloated donkey, swayed above the children, who scrambled for candy with the urgency of tiny pirates. Molly gestured toward the mountain of presents, bright boxes threatening to topple. She tossed the glowing frisbee, its neon trail arcing through the air like a comet. The children gasped, pointing at the luminous disc, convinced it was part of the show. While the audience shrieked with delight, Molly and Bill swooped in, scooping gifts into the cart with the precision of seasoned surgeons. The cart rattled away, its wheels humming a quiet victory song. In the kitchen, the birthday cake sat untouched, its candles flickering like tiny beacons. As the final note of the magic trick faded, the thieves slipped out, the front door closing with a soft click. Outside, streetlights cast long shadows, and the night air smelled of frosting and mischief forever.
created_at
"2026-02-17T09:36:31.991217+00:00"
2/17/2026, 9:36:31 AM
model
"minimax/minimax-m2.5-20260211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3649
moderation_latency
(null)
generation_time
313043
tokens_prompt
77
tokens_completion
17430
native_tokens_prompt
101
native_tokens_completion
17376
native_tokens_completion_images
(null)
native_tokens_reasoning
16698
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
0.0208815
router
(null)
provider_responses
0
id
"05e36866ea4b258cc0237d40b6dade02"
status
200
is_byok
false
latency
3649
endpoint_id
"3afb00c4-6135-4c55-96e9-6befa9679b06"
provider_name
"Minimax"
model_permaslug
"minimax/minimax-m2.5-20260211"
api_type
"completions"
id
"gen-1771320678-HJGpEuYMGTcvcV4uZ0zC"
upstream_id
"05e36866ea4b258cc0237d40b6dade02"
total_cost
0.0208815
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
500
0.01%
Dialogue to Total Word Ratio
Ratio: 36.00%, Deviation: 14.00%
neededClean
false
wordsTotal
500
wordsDialogue
180
50.0028%