NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K4T3TJ7H7708T9284JQZA2
Run Details
Model:
Muse Spark 1.2 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
42.1s
Cost:
$0.029635
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.95%
Dialogue to Total Word Ratio
(details)
99.9751%
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
The van smelled faintly of old pizza and desperation. Molly sat cross-legged on the floor among tangled extension cords, studying the floor plan of Tiny Tots Party Palace taped to the dashboard. Bill leaned against the driver's seat, holding two lukewarm juice boxes he'd stolen from a gas station. Outside, inflatable castles wobbled in the wind and a banner read Happy 6th Birthday Leo! "Bill, remind me again why we're robbing a children's party?" "Because the parents went overboard. There's a pile of presents the size of Everest in there." She traced a route with a highlighter, from the emergency exit through the kitchen to the gift table. The plan was ridiculous and brilliant in equal measure. Bill had insisted on wearing a borrowed uniform. "We have sunk to a new low. We used to rob banks." "Banks have cameras and armed guards. This place has a clown and a ball pit." He looked less like an entertainer and more like a defeated magician who had lost a fight with a glitter cannon. Molly stifled a laugh and tried to focus. The afternoon sun made the van unbearably hot. "That clown is six foot four and looks like he wrestles bears for fun." "Trust me. I've got a plan. I distract him with balloon animals while you grab the gifts." "Your balloon animals look like sad potatoes. The kids will riot." Through the windshield they could see mothers arranging cupcakes, fathers inflating balloons, and a mountain of brightly wrapped presents guarded only by a sleepy teenager in a party hat. Molly sighed and folded the map. "Kids love potatoes. Besides, you are the one who suggested the party disguise." "I suggested we dress as parents, not as a discount magician and his reluctant assistant." "You look great. That apron says you bake cookies and make good life choices." She checked her watch. The clown was due for a break at three. That was their window, seven minutes to get in, grab the loot, and vanish before the cake arrived. "This apron says Kiss the Cook and it has a stain I don't want to investigate." "Focus. We go in at three, straight to the gift table, laundry bags ready." Bill adjusted his oversized bow tie and wiped sweat from his forehead, looking tragically unconvincing. Molly shook her head, but she was already reaching for the door handle. "And if someone asks what we're doing?" "We say we're collecting presents for the birthday boy's special surprise upgrade." "Leo is six. He will notice when all his presents vanish into a laundry bag." "He'll think it's magic. Kids believe anything if you add enough glitter." The parking lot was chaos, screaming children everywhere, and no one would notice two more adults slipping inside. "Fine. But we split the loot evenly and you never make balloon potatoes again." "Deal. Now smile. We're about to be the best worst parents this party has ever seen." Absolutely perfect. "Let's steal some toys and pray silently."
created_at
"2026-09-03T08:05:21.369Z"
9/3/2026, 8:05:21 AM
model
"meta/muse-spark-1.2-20260805"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3573
moderation_latency
(null)
generation_time
42034
tokens_prompt
75
tokens_completion
751
native_tokens_prompt
68
native_tokens_completion
6953
native_tokens_completion_images
0
native_tokens_reasoning
6286
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
0.02963525
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788422721-AO0dhT4qc1g11nRnqXz5"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788422721-pxwdPkBX55T4xtW870bR"
upstream_id
"resp_6a992a4190e907d0065b4305"
provider_responses
0
endpoint_id
"ffc8e76e-808a-44d2-bd21-c6ac16e721cb"
id
"resp_6a992a4190e907d0065b4305"
is_byok
false
latency
1413
model_permaslug
"meta/muse-spark-1.2-20260805"
provider_name
"Meta"
status
200
total_cost
0.02963525
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
500
99.95%
Dialogue to Total Word Ratio
Ratio: 49.90%, Deviation: 0.10%
neededClean
false
wordsTotal
501
wordsDialogue
250
99.9751%