NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD60WK9AF3R85SSNV41TMB9
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
25.2s
Cost:
$0.017702
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
92.94%
Dialogue to Total Word Ratio
(details)
95.8285%
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
Messages
Meta
AI
Molly spread the catering flyer across the hood of their getaway vehicle, a dented ice cream van that still played its jingle at inappropriate moments. The suburban house ahead was drowning in pink streamers and screaming. "Bill, if we get caught stealing from five-year-olds, we can never show our faces in this town again." Bill adjusted his oversized clown nose and immediately regretted it as it squeaked loudly enough to alert the neighborhood watch. He carried a bag of deflated balloons like they were explosives. "Molly, we already can't show our faces. That's why we're wearing clown wigs." The plan itself was written on the back of a napkin stolen from a pizza place, mostly because Molly had spilled sauce on the front. "It's a princess party. There will be at least twenty presents, all sticky with frosting. We go in through the side gate during musical chairs." Outside the fence, a dozen small children in paper crowns were chasing each other with juice boxes, while exhausted parents clustered near the cake table pretending to enjoy conversation. "Musical chairs is dangerous. Those kids have no mercy. Last time I lost a shoe." Bill stared at the mountain of brightly wrapped presents stacked near the bouncy castle, each one taller than the birthday girl herself. "Focus. You distract the parents with balloon animals. I'll grab the present mountain and load it into the van's freezer." Molly checked her watch, which was actually a sticker that said princess time, and nodded toward the side gate that had been left conspicuously open for catering staff. "What if they want something complicated, like a giraffe on a skateboard? I can only do snakes. Very nervous snakes." "Then make nervous snakes! Tell them it's modern art. Just keep them looking at you while I make the presents disappear." The ice cream van's freezer hummed optimistically, ready to be filled with plunder instead of popsicles. "This feels wrong, Molly. These kids actually wrote thank you notes in advance. One says thanks for coming, Mr. Clown Burglar." "That's our legacy. The most polite crime spree in history. Now, do you have the escape playlist?" "Yes. It's all Baby Shark remixes. The kids will be too busy dancing to notice the loot." They both took a deep, ridiculous breath. "Perfect. Operation Birthday Snatch is a go. And if we fail, we pretend we were hired entertainment." Inside, the birthday girl was attempting to wear all her new tiaras at once, wobbling dangerously under the sparkling weight, completely unaware that two extremely unprofessional criminals were plotting her gift table's demise. "We were never hired. We were barely tolerated. Let's steal those blocks." "And if anyone asks, we are redistributing joy from children who already have too many plastic dinosaurs to adults who have none." Molly grinned, Bill sweated, and somewhere a child screamed because someone stole the last cupcake. "That is the dumbest Robin Hood speech I've ever heard and I love it."
created_at
"2026-07-25T17:43:59.856Z"
7/25/2026, 5:43:59 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
21375
moderation_latency
(null)
generation_time
25140
tokens_prompt
75
tokens_completion
764
native_tokens_prompt
225
native_tokens_completion
4099
native_tokens_completion_images
0
native_tokens_reasoning
3461
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
0.017702
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f5e0964bf9af53824202"
is_byok
false
latency
331
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-1785001439-moVIFMV1BgSM88Xgf4N8"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001439-ylSOP7agbw59a8DPVDyO"
upstream_id
"resp_6a64f5e0964bf9af53824202"
total_cost
0.017702
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
98.71%
Matches word count
n/a
neededClean
false
words
494
92.94%
Dialogue to Total Word Ratio
Ratio: 51.21%, Deviation: 1.21%
neededClean
false
wordsTotal
496
wordsDialogue
254
95.8285%