NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXPGKC5QSP2WGY1G6KS2CKD
Run Details
Model:
Mistral Large 3
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
16.7s
Cost:
$0.001284
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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
The fluorescent lights of the diner buzzed like a swarm of angry bees, casting a sickly glow over the chipped Formica table where Molly and Bill sat. A half-eaten plate of fries congealed between them, forgotten in favor of the blueprint spread across the table. Molly tapped a manicured nail against the paper, her lips pursed in concentration. "You’re telling me we’re hitting a *kids’ party*?" Bill said, scratching his stubble. "I’ve robbed banks, I’ve lifted jewels, but this feels… wrong." Molly rolled her eyes. "Oh, please. You once stole a priest’s collection plate mid-sermon. This is practically charity work." "Yeah, but the priest *expected* it. These are *children*, Mol. They cry when you take their stuff." She leaned forward, her voice dropping to a conspiratorial whisper. "Exactly. Who’s gonna suspect a couple of thieves at a six-year-old’s birthday bash? The cops? They’ll be too busy laughing at the idea to actually show up." Bill groaned, rubbing his temples. "I can already see the headlines: *‘Notorious Thieves Nabbed After Heist Gone Wrong—Culprits Still Stuck in Ball Pit.’*" Molly smirked. "Admit it, you’re just mad because you’ll have to wear a clown nose." "Absolutely not. I draw the line at face paint." "Fine. You can be the magician. I’ll be the *distraction*." She wiggled her fingers like she was casting a spell. "Kids love magic tricks. Especially the ones where you make their presents disappear." Bill sighed, pinching the bridge of his nose. "We’re gonna need a getaway plan that doesn’t involve a minivan." "Already on it. I rented a ice cream truck. Classic, unsuspicious, and if we get caught, we can just say we’re lost." "An ice cream truck? That’s your big plan?" Molly grinned. "It’s got a freezer. We can stash the loot in there. Plus, if the cops chase us, we can just start handing out popsicles. They’ll be too busy licking their cones to arrest us." Bill stared at her for a long moment before shaking his head. "You’re a menace." "And you love it." He exhaled sharply, then pointed at the blueprint. "Alright, fine. Walk me through it again. How do we even get in?" Molly’s grin widened. "Easy. We pose as the entertainment. I called the parents, said we’re the *Amazing Molly and Bill*, world-famous party magicians. They bought it hook, line, and sinker." Bill groaned. "We don’t even *do* magic." "Details." She waved a hand dismissively. "We’ll wing it. How hard can it be to pull a rabbit out of a hat?" "Harder than you think, considering we don’t *have* a rabbit." Molly reached into her bag and pulled out a stuffed bunny. "Ta-da." Bill blinked. "Where the hell did you get that?" "Stole it from a baby at the grocery store." "You *what*?" She shrugged. "Relax, it was just sitting in the cart. The kid was too busy eating paste to notice." Bill buried his face in his hands. "I need a drink." Molly slid a flask across the table. "Already poured you one. Now, are we doing this or not?" He took a long swig, then set the flask down with a resigned sigh. "Fine. But if I get arrested, I’m telling them you made me do it." Molly clapped her hands together. "That’s the spirit! Now, let’s go over the escape route one more time—" "God help us," Bill muttered.
created_at
"2026-02-20T14:15:59.131Z"
2/20/2026, 2:15:59 PM
model
"mistralai/mistral-large-2512"
1/1/2512, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
427
moderation_latency
(null)
generation_time
16630
tokens_prompt
77
tokens_completion
881
native_tokens_prompt
69
native_tokens_completion
833
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.001284
router
(null)
provider_responses
0
endpoint_id
"fa718841-07ea-4b7e-b8a3-6069545c7e6a"
id
"5a3e1b43fbd54c99819479c41c3df102"
is_byok
false
latency
427
model_permaslug
"mistralai/mistral-large-2512"
1/1/2512, 12:00:00 AM
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771596959-tAJPKTxJit8J8BustWwG"
upstream_id
"5a3e1b43fbd54c99819479c41c3df102"
total_cost
0.001284
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
566
0.00%
Dialogue to Total Word Ratio
Ratio: 67.31%, Deviation: 37.31%
neededClean
false
wordsTotal
566
wordsDialogue
381
0.0000%