NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5Q4JT8VC9M8MP976M3VME
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
18.8s
Cost:
$0.013456
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9906%
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
"Okay, so the target is a six-year-old's birthday party," Molly said. "Right. High security, huh?" Bill replied. "Extreme. There's a clown, a bouncy castle, and at least four moms with juice boxes." "Juice boxes? We didn't train for juice boxes." "We trained for lasers, Bill. This is worse. Capri-Sun moms have eyes everywhere." "What's the loot?" "Presents. Mountain of them. Legos, bikes, probably a Nintendo Switch with sticky fingerprints." "So we go in disguised as... entertainers?" "Exactly. You are Mr. Wiggles the Magician." "I hate kids." "Perfect, they hate you back. You'll fit right in." "And you?" "I'll be the face painter. I'll cause a distraction. You grab the pile." "What if they want balloon animals?" "Make them. Badly. Cause panic." "Genius. What about the birthday boy?" "Bribe him with cake." "What if he cries?" "Then we cry louder. No one suspects crying adults." Molly grinned, adjusting her glittery smock. "Remember, in and out, sixty seconds, nobody gets frosted." "Got it. And if we get caught?" Bill swallowed hard, staring at the rainbow invitation. "We tell them we're his uncles. Creepy, disappointed uncles." "Perfect plan." Molly winked. "Let's steal some joy." Bill sighed, "For the kids? No, for Legos. Absolutely. Let's go."
created_at
"2026-07-25T17:38:40.353Z"
7/25/2026, 5:38:40 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
17657
moderation_latency
(null)
generation_time
18674
tokens_prompt
75
tokens_completion
323
native_tokens_prompt
225
native_tokens_completion
3100
native_tokens_completion_images
0
native_tokens_reasoning
2770
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
0.01345625
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f4a0537dca26410642a3"
is_byok
false
latency
242
model_permaslug
"meta/muse-spark-1.1-20260709"
provider_name
"Meta"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1785001120-ZsObfR377wuzN6kYiU0L"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001120-8nYdQicxxLvIkrG4GCPN"
upstream_id
"resp_6a64f4a0537dca26410642a3"
total_cost
0.01345625
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Meta"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
100.00%
Dialogue to Total Word Ratio
Ratio: 89.27%, Deviation: 0.73%
neededClean
false
wordsTotal
205
wordsDialogue
183
99.9906%