NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-01-01KQHR8C0PJC28C7CEEA1MTKB4
Run Details
Model:
Grok 4.3 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
3m 17s
Cost:
$0.035378
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.62%
Dialogue to Total Word Ratio
(details)
49.8110%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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
In the middle of their time worn hideout, which was located above an old bakery that provided cover noise for their discussions, Molly and Bill were deep into planning this particular comedic heist that involved sneaking into a lively children's party to steal all the birthday presents on display. The table in the center was covered with various tools of their trade including colorful wigs for the disguises, oversized shoes that would complete the clown outfit, and large empty duffel bags meant for carrying their ill gotten gains from the party. Everything had been prepared meticulously over the previous day to ensure the operation went off without a hitch and produced the usual laughs they both enjoyed so much during their illegal activities. Molly detailed the steps while Bill listened intently, ready to add his humorous twist to the proceedings with his natural talent for comedy. She laid out a sheet of paper with the party venue sketched roughly in pencil, highlighting the gift table area with a big circle for emphasis on the target location during the event. Molly told him the basics first. "Bill, we will dress as clowns and infiltrate the party. I'll distract with juggling and you grab the presents." The words were spoken with confidence born from many past missions they had successfully completed without getting caught by authorities. Bill replied simply, "Got it. The clown act will be hilarious. Kids love a good show and it masks our true goal." He practiced a honk from an imaginary nose horn to demonstrate his readiness for the role in front of the children. Then they discussed the timing. "We go in right after the guests arrive," Molly added. "The presents are on a table by the door so you can load them quickly into our bags while I keep the attention on the performance." She rolled her eyes at his antics but appreciated the enthusiasm he brought to every job they undertook together without fail. Bill nodded and said, "What about the escape? We need to leave before they notice the missing gifts." His expression turned serious for a moment as he considered the logistics involved in making a clean getaway after the grab was complete. "Through the side kitchen door," she answered. "It leads straight to our parked van. Timing is key so no one sees us leaving with the haul." They both visualized the van's location in the alley behind the building and mapped out the quickest path to it in their minds for efficiency. Bill smiled thinking about it. "This will be easy compared to our usual jobs. No lasers or dogs, just kids and cake. I can handle the silly voices to make it convincing." He laughed at the image of children cheering for their performance while they slipped away with the loot undetected in the confusion. Molly gave one last piece of advice. "Stay in character at all times and avoid talking too much to the grown ups. This will be a blast and fill our pockets with toy sales later." With that, they began packing their bags with clown accessories and empty sacks for the upcoming theft as the sun set outside their window signaling it was time to move soon on this new adventure.
created_at
"2026-05-01T12:29:44.347Z"
5/1/2026, 12:29:44 PM
model
"x-ai/grok-4.3-20260430"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
197012
moderation_latency
(null)
generation_time
197092
tokens_prompt
77
tokens_completion
1665
native_tokens_prompt
184
native_tokens_completion
14086
native_tokens_completion_images
(null)
native_tokens_reasoning
13478
native_tokens_cached
64
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"
usage
0.0353778
router
(null)
provider_responses
0
endpoint_id
"45623cb8-18e5-4b32-8fc4-85d05439982d"
id
"6df8f4cb-cfe3-95e9-9cd2-50137b29a55b"
is_byok
false
latency
91
model_permaslug
"x-ai/grok-4.3-20260430"
provider_name
"xAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777638584-Gov6oGSuCKhRoAYMDKz7"
session_id
(null)
api_type
"completions"
id
"gen-1777638584-6KZSJIcYKCT6s7p3cvTp"
upstream_id
"6df8f4cb-cfe3-95e9-9cd2-50137b29a55b"
total_cost
0.0353778
cache_discount
0.0000672
upstream_inference_cost
0
provider_name
"xAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
545
99.62%
Dialogue to Total Word Ratio
Ratio: 30.28%, Deviation: 0.28%
neededClean
false
wordsTotal
545
wordsDialogue
165
49.8110%