NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD4NYFEQA5Q279N3YBRXSCK
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
12.2s
Cost:
$0.008649
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
99.57%
Dialogue to Total Word Ratio
(details)
87.3641%
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
Molly pressed the blueprints against the van window while Bill steered with his knees. "Listen, Bill, there are twenty screaming six-year-olds in there. That's basically laser security." Bill snorted and nearly dropped a juice box. "So what's the plan? We walk in as clowns?" "Better. You're the magician. I'm your incredibly reluctant rabbit." Molly tapped the bouncy castle on the map. "The presents are stacked by the cake. We go in during musical chairs." "Right, because no one notices two adults fighting toddlers for chairs." "Exactly. Grab the loot while they're distracted. Then we vanish." Bill frowned at his oversized shoes. "What if the birthday boy cries? I can't handle crying." "Then we give him back one present. We have standards." Molly folded the blueprints into a paper crown and placed it on Bill's head solemnly. "Perfect. Now you look like you belong at a hostage negotiation with juice." Bill adjusted the crown, sighed deeply, and started rehearsing balloon animals with menace. "Let's roll." The van smelled of old frosting and bad decisions. Outside, parents parked minivans, oblivious to the criminal masterminds discussing larceny beside a trampoline. Molly checked her watch. Two hours until cake, chaos, and the greatest toy heist ever attempted. Both thieves nodded, terrified and weirdly excited. Ready for disaster.
created_at
"2026-07-25T17:20:32.757Z"
7/25/2026, 5:20:32 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
10597
moderation_latency
(null)
generation_time
12160
tokens_prompt
75
tokens_completion
357
native_tokens_prompt
225
native_tokens_completion
1969
native_tokens_completion_images
0
native_tokens_reasoning
1643
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
0.0086495
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f06196d70d0a2b0549e1"
is_byok
false
latency
285
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-1785000032-VWFbOvOSLxymhcbB71nz"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000032-x6Xo6Cm4rlwtjQIuBViu"
upstream_id
"resp_6a64f06196d70d0a2b0549e1"
total_cost
0.0086495
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
75.16%
Matches word count
n/a
neededClean
false
words
213
99.57%
Dialogue to Total Word Ratio
Ratio: 47.44%, Deviation: 2.56%
neededClean
false
wordsTotal
215
wordsDialogue
102
87.3641%