Run: 2026-02-24-01KJ8VEHAH3EVEDT79KDNQGN06

Run Details

Model:
Aion 2.0
Duration:
27.8s
Cost:
$0.001854
Provider:
AionLabs

Evaluation summary

Score Evaluator
Details Link
100.00% Matches word count (details)
0.00% Dialogue to Total Word Ratio (details)
49.9995% 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

AI
The rusted van smelled of old pizza and regret. Molly tapped a laminated schematic of “Happy Land” party venue against her knee. Bill adjusted the fake moustache he was wearing for “mental preparation.” “The target is a six-year-old named Timmy,” Molly said, her voice low. “His party runs from two to four PM. Peak present-opening occurs at approximately three-thirty.” “The sweet spot,” Bill nodded, squinting at his own copy of the schematic. “You’re sure about the security?” “A single, forty-five-year-old mother named Brenda. Primary weapons: guilt and a whistle. Our intel suggests she’ll be distracted by juice spillage and the potential for a piñata-related lawsuit.” Bill leaned back, cracking his knuckles. “So we go in as clowns. Classic misdirection.” “We are not going in as clowns,” Molly sighed. “I vetoed the clowns. My research indicates a seventy percent increase in childhood phobias linked to clown-based party entertainment. We’d be memorable.” “Fine. Magicians?” “Also vetoed. You still can’t do the French Drop without dropping the actual coin. We’re going in as caterers from ‘Fancy Finger Foods.’” She held up a cheap polo shirt with a embroidered logo of a tiny sandwich. Bill looked crestfallen. “Catering lacks panache. Where’s the flair?” “The flair is in not getting tackled by a dad in a ‘Kiss the Chef’ apron. Now, listen. At three-twenty-five, you create a diversion by ‘accidentally’ releasing the helium balloons into the ceiling fan.” “Creating aerial chaos. I like it.” “While the children are screaming at the balloon massacre, I’ll move to the gift table, here.” She pointed to the schematic. “I’ll load the presents into our reinforced gift bags. You’ll have the van running by the fire hydrant.” Bill scratched his chin. “What’s the haul looking like?” Molly consulted her tablet. “Conservative estimate: eighteen to twenty-five gifts. Mostly plastic, medium to high value. A couple of those talking dinosaur things, a junior chemistry set—which we are *not* opening before the job—and a suspicious number of gift cards.” “Gift cards are clean,” Bill mused. “Untraceable. Perfect for a birthday score.” “It’s not a ‘score,’ Bill. It’s a systematic asset relocation from a suburban living room.” “Same thing. What about the cake?” “The cake is not part of the operation.” “But it’s a sheet cake from Costco. With those delicious sugar roses.” “Focus! We are professionals. We are in and out in ninety seconds. No cake, no goody bags, no hitting the pinata on the way out. Understood?” Bill slumped. “Understood. But if there’s a loose gummy bear on the floor, all bets are off.” Molly stared at him, dead-eyed. “The success of this operation hinges on your ability to ignore floor candy. Can you handle that?” He took a deep, theatrical breath. “For the team. For the presents. I can resist.” “Good.” Molly checked her watch. “We move in one hour. Remember, the greatest threat isn’t the parents. It’s a hyper-vigilant eight-year-old who’s seen too many spy movies.” “Yeah,” Bill said, puffing out his chest. “But he hasn’t seen us.”
created_at"2026-02-24T22:13:53.112Z" 2/24/2026, 10:13:53 PM
model"aion-labs/aion-2.0-20260223"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1975
moderation_latency(null)
generation_time27750
tokens_prompt77
tokens_completion1257
native_tokens_prompt170
native_tokens_completion1074
native_tokens_completion_images(null)
native_tokens_reasoning374
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.0018544
router(null)
provider_responses
0
endpoint_id"1e93b0bb-eb0f-49bc-8fda-947105413b86"
id"c7254ab8-81a4-4923-ba0e-a7d6349d0a85"
is_byokfalse
latency107
model_permaslug"aion-labs/aion-2.0-20260223"
provider_name"AionLabs"
status200
api_type"completions"
id"gen-1771971233-QWZayKXskvjxFHHOLZfu"
upstream_id"c7254ab8-81a4-4923-ba0e-a7d6349d0a85"
total_cost0.0018544
cache_discount(null)
upstream_inference_cost0
provider_name"AionLabs"

Evaluation details

Result Evaluator Details Meta Data
100.00% Matches word count n/a
neededCleanfalse
words501
0.00% Dialogue to Total Word Ratio
Ratio: 78.92%, Deviation: 28.92%
neededCleanfalse
wordsTotal517
wordsDialogue408
49.9995%