NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-01-01KQHR762YH6CHTG5A7E2NPS1N
Run Details
Model:
Grok 4.3 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 9s
Cost:
$0.018218
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 and Bill parked their van near the children's party at the park, scanning the area for the best way to sneak in and steal the presents without being caught. They planned to use silly costumes like oversized hats and fake noses to pass as entertainers. Timing was key since the party was loud with music and laughter from all the excited kids celebrating. Bill pointed to the layout while Molly mapped their escape route through the trees. Bill whispered, "Enter through the back gate now." Molly nodded and replied, "Good idea but watch the noisy kids carefully." Bill agreed, "Ok grab the presents and run." They moved into position, feeling confident about their very clever heist that would net them tons of unwrapped gifts by using the chaos as cover. The comedic element of two adults acting goofy among toddlers made them chuckle under their breath. With the parents oblivious and focused on supervising birthday games, Molly and Bill inched closer, ready for the moment to strike and fill their sacks full of surprises meant for the little ones. Success depended on speed and discretion, avoiding any mix ups with the actual party staff who might question their presence.
created_at
"2026-05-01T12:29:05.506Z"
5/1/2026, 12:29:05 PM
model
"x-ai/grok-4.3-20260430"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
67993
moderation_latency
(null)
generation_time
69365
tokens_prompt
77
tokens_completion
1918
native_tokens_prompt
184
native_tokens_completion
7222
native_tokens_completion_images
(null)
native_tokens_reasoning
6996
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
0.0182178
router
(null)
provider_responses
0
endpoint_id
"45623cb8-18e5-4b32-8fc4-85d05439982d"
id
"3618839f-3848-963a-8276-f29c792e0519"
is_byok
false
latency
105
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-1777638545-VkTa2ZrXruakANLjssMN"
session_id
(null)
api_type
"completions"
id
"gen-1777638545-j4NcNZrqHrmkVDvxeCmk"
upstream_id
"3618839f-3848-963a-8276-f29c792e0519"
total_cost
0.0182178
cache_discount
0.0000672
upstream_inference_cost
0
provider_name
"xAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%