NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-26-01KJCRTTSHPMQFSP3DHQ7FZ5J0
Run Details
Model:
LFM2 24B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
14.4s
Cost:
$0.000039
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
98.77%
Dialogue to Total Word Ratio
(details)
59.4813%
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
The neon lights of the children’s party buzzed like angry bees as Molly leaned against the brick wall, her eyes darting toward the open door. “Bill, you sure this is the plan?” she whispered, adjusting her mask. Bill adjusted his gloves, grinning. “Absolutely. The kids’ll be too busy chasing balloons to notice us.” He paused, squinting at the room. “Wait—what if they spot us?” Molly snorted. “Then we’ll blame the clown. Classic misdirection.” She pulled out a tiny flashlight, flicking it on. “See that pile of presents? That’s where we strike.” Bill nodded, tapping his temple. “Easy. But first, we need a distraction. Maybe the cake?” “Too risky,” she said, rolling her eyes. “Last time you tried ‘distracting’ with cake, the dog ate half the frosting.” He laughed. “Hey, that dog’s got taste.” Molly smirked. “Fine. Let’s go. But if we get caught, I’m blaming the clown.” Bill raised an eyebrow. “Deal. Now, where’s the nearest window?” They slipped inside, the party’s laughter echoing behind them as Molly muttered, “This’ll be the easiest heist yet.” Bill grinned. “Easiest? You’re on.”
created_at
"2026-02-26T10:45:14.413Z"
2/26/2026, 10:45:14 AM
model
"liquid/lfm-2-24b-a2b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1129
moderation_latency
(null)
generation_time
7560
tokens_prompt
77
tokens_completion
325
native_tokens_prompt
75
native_tokens_completion
309
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
0.00003933
router
(null)
provider_responses
0
endpoint_id
"b5f259c3-1e77-40d6-8fa4-161cdf0e4a7c"
id
"oYued6z-2j9zxn-9d3eda0ec3b3e505"
is_byok
false
latency
1129
model_permaslug
"liquid/lfm-2-24b-a2b-20260224"
provider_name
"Together"
status
200
api_type
"completions"
id
"gen-1772102714-p1Ppok5V398B0JGRSFOl"
upstream_id
"oYued6z-2j9zxn-9d3eda0ec3b3e505"
total_cost
0.00003933
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
Evaluation details
Result
Evaluator
Details
Meta Data
20.19%
Matches word count
n/a
neededClean
false
words
180
98.77%
Dialogue to Total Word Ratio
Ratio: 53.33%, Deviation: 3.33%
neededClean
false
wordsTotal
180
wordsDialogue
96
59.4813%