NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD50TDGVK8SZ8F7HWPS1YQW
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.0s
Cost:
$0.005619
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
53.88%
Dialogue to Total Word Ratio
(details)
73.7644%
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, walk me through it again," Bill whispered. "Simple. We go in, we grab the presents, we get out rich," Molly said. "Rich? It's Paw Patrol stickers and half-eaten cupcakes," Bill said. "Don't underestimate the sticker resale market," Molly said. "There's like eight seven-year-olds in there. One of them is already crying," Bill said. "Perfect cover. Chaos is our friend," Molly said. "Sure, but the mom hired a clown. Clowns remember faces," Bill said. "We'll wear clown makeup. Foolproof," Molly said. "You said that about the petting zoo job and you got headbutted by a goat," Bill said. "That goat had it coming. Look, the pile is huge. I saw a LEGO Death Star," Molly said. "Okay. What's our code word if it goes south?" Bill asked. "We scream birthday and run," Molly said. "That's terrible. What if they think we're part of the entertainment?" Bill said. "Then we juggle. You practiced," Molly said. "I can't juggle. I have carpal tunnel from our last brilliant plan," Bill said. "Fine. We waddle in, act like parents who lost their kid, grab the table, bolt. Easy," Molly said. "That's kidnapping and theft now," Bill said. "It's called multitasking. Ready?" Molly asked. "No. Absolutely not," Bill said. "Great. Let's go," Molly said.
created_at
"2026-07-25T17:26:29.049Z"
7/25/2026, 5:26:29 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
7588
moderation_latency
(null)
generation_time
8823
tokens_prompt
75
tokens_completion
318
native_tokens_prompt
225
native_tokens_completion
1256
native_tokens_completion_images
0
native_tokens_reasoning
942
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
0.00561925
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f1c54f31895bdc064601"
is_byok
false
latency
502
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-1785000389-atLsVlMHOBE7F96YSzZk"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000389-Hv7zd7J0sdojlqwoEnLF"
upstream_id
"resp_6a64f1c54f31895bdc064601"
total_cost
0.00561925
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
93.65%
Matches word count
n/a
neededClean
false
words
209
53.88%
Dialogue to Total Word Ratio
Ratio: 81.13%, Deviation: 8.87%
neededClean
false
wordsTotal
212
wordsDialogue
172
73.7644%