NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K5TP68CB3G2Q98S0VXKS7Y
Run Details
Model:
Muse Spark 1.2 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
16.7s
Cost:
$0.021581
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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, this is a new low even for us," Bill whispered. "Oh please, have you seen the price of Legos lately?" Molly replied. "Yeah but they're guarded by like ten screaming sugar-high kids and one angry clown," Bill said. "That's why the clown outfit is perfect. They'll never suspect the clown," Molly said. "You want me to dress as a clown? I hate clowns. They hate me," Bill muttered. "You owe me after the aquarium job. You dropped the penguin," Molly snapped. "I did not drop him, he slipped! Look, can't we just rob a bank like normal thieves?" Bill pleaded. "Banks have lasers. This house has a bouncy castle. This is easier," Molly insisted. "Until little Timmy sees us stuffing his presents into a sack," Bill said. "Then we offer him a balloon animal and run. Simple, fast, and nobody cries except maybe you," "Deal. Just try not to scare the kids before we get the loot," "Me scare them? You're the one who pops balloons for fun, you absolute balloon-popping maniac," "Let's go steal that bouncy castle too while we're at it." "Fine. But if I have to make balloon animals I'm demanding half the Legos," Bill sighed.
created_at
"2026-09-03T08:23:08.75Z"
9/3/2026, 8:23:08 AM
model
"meta/muse-spark-1.2-20260805"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2856
moderation_latency
(null)
generation_time
16674
tokens_prompt
75
tokens_completion
313
native_tokens_prompt
68
native_tokens_completion
5058
native_tokens_completion_images
0
native_tokens_reasoning
4753
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
service_tier
"auto"
usage
0.0215815
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788423788-IvsBplCGNcVkRb2xmQLy"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788423788-H8O1a1RZsXRpxb5BFr5Y"
upstream_id
"resp_6a992e6c3466d3cbdc7a4ff4"
provider_responses
0
endpoint_id
"ffc8e76e-808a-44d2-bd21-c6ac16e721cb"
id
"resp_6a992e6c3466d3cbdc7a4ff4"
is_byok
false
latency
268
model_permaslug
"meta/muse-spark-1.2-20260805"
provider_name
"Meta"
status
200
total_cost
0.0215815
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Meta"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 90.10%, Deviation: 0.10%
neededClean
false
wordsTotal
202
wordsDialogue
182
100.0000%