NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHNFYPHR7KHJ5C1Q59XA3272
Run Details
Model:
Minimax M2.5
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
6m 14s
Cost:
$0.017945
Provider:
Novita
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
0.01%
Dialogue to Total Word Ratio
(details)
49.8791%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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
Moonlight bathed the Hendersons' cul-de-sac as a distant birthday jingle played. Molly hid behind a garden gnome; Bill, in a huge polka-dot shirt and a clown wig, whispered his plan. Molly: "Bill, I swear, if we get caught, I'm blaming you for the clown wig." Bill: "Hey, it's genius. The kids will be too busy fighting over the last slice of pizza to notice a couple of extra 'gift grabbers.'" Molly: "Extra? We're planning to take every single present, Bill. That's like ten plushes, a dozen toys, and at least three video games." Bill: "Exactly! We'll slip in during the cake cutting. The parents will be all 'aww' and the kids will be staring at the candles. We'll swoop in, grab the loot, and exit through the back door like ninja librarians." Molly: "Ninja librarians? That's not a thing." Bill: "It is now. I watched a documentary." Molly: "You watched a cooking show about lasagna." Bill: "Okay, I may have been distracted, but the plan is solid. We'll hide the bag under the table, pretend we're the entertainment, and when the kids start opening presents, we swap them with empty boxes." Molly: "Empty boxes? That's cruel. The kids will cry." Bill: "Not if we replace the boxes with fake gifts—little notes saying 'To the future thief, keep dreaming.'" Molly: "That's... actually hilarious. But we need a distraction. The clown is already booked." Bill: "I already bribed the clown. He's going to do a magic trick that ends with a confetti explosion. We'll use the chaos." Molly: "And if the clown chickens out?" Bill: "I'll give him a motivational speech about job security. He'll love it." Molly: "Alright, what about the parents? They'll be watching like hawks." Bill: "We'll wear these." He held up tiny party hats with hidden cameras. Molly: "Those are adorable. And creepy." Bill: "Exactly what we want. They'll think we're just enthusiastic guests. When the music stops, we grab the presents and blend into the crowd." Molly: "What if someone recognizes us from the neighborhood watch?" Bill: "We'll claim we're from the 'Party Planning Committee for Underprivileged Kids.' They'll eat it up." Molly: "You're insane." Bill: "Insane is my middle name. Actually, it's 'Mischief,' but the kids won't know." Molly: "Okay, we go in at eight, grab everything by eight fifteen, and meet at the van." Bill: "Van? I thought we were using the bicycle cart." Molly: "The bicycle cart is for the getaway. The van is for the heavy loot." Bill: "Right. I forgot we have a whole stash of glittery gift wrap." Molly: "Don't forget the glitter bomb. If anything goes wrong, we release it." Bill: "Glitter bomb? That's the perfect exit. It'll cover our tracks and make us sparkle." Molly: "Let's move. The party starts in ten minutes, and I don't want to miss the cake." Bill: "Onwards, my partner in crime." They slipped from the shadows, footsteps muffled by balloons, and approached the glowing house, ready for the suburb's most audacious party heist.
created_at
"2026-02-17T09:53:40.399986+00:00"
2/17/2026, 9:53:40 AM
model
"minimax/minimax-m2.5-20260211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1656
moderation_latency
(null)
generation_time
374402
tokens_prompt
77
tokens_completion
14263
native_tokens_prompt
101
native_tokens_completion
14929
native_tokens_completion_images
0
native_tokens_reasoning
14220
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
0.0179451
router
(null)
provider_responses
0
id
"ae429d0136e2bfca93a12f6e9e1072d2"
status
200
is_byok
false
latency
1656
endpoint_id
"05387b87-6e10-4520-87e9-be7c49693ba1"
provider_name
"Novita"
model_permaslug
"minimax/minimax-m2.5-20260211"
api_type
"completions"
id
"gen-1771321645-aoGvBYoXpPy8wt1ToYXJ"
upstream_id
"ae429d0136e2bfca93a12f6e9e1072d2"
total_cost
0.0179451
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
504
0.01%
Dialogue to Total Word Ratio
Ratio: 83.33%, Deviation: 13.33%
neededClean
false
wordsTotal
504
wordsDialogue
420
49.8791%