NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8VQQSXRAXPXG3X97YBJ030
Run Details
Model:
Grok 4.3
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.5s
Cost:
$0.000648
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
50.10%
Dialogue to Total Word Ratio
(details)
25.0516%
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
Molly stared at the floor plan, whispering, “Bill, this kiddie party’s loaded with presents, but that clown entertainer scares me.” Bill chuckled, “Scared of a balloon artist? We hit at two when the parents are busy arguing over cake.” “Fine, but the alarm on the gift table—how do we bypass it without waking the moms?” Molly hissed. Bill grinned, “I lift the bags while you distract with that fake raffle ticket. Easy peasy.” Molly frowned, “What if a kid spots us and yells? Those little monsters bite.” “Throw candy one way, run the other,” Bill replied, tying his mask. “Just remember,” Molly warned, “no hitting anyone with piñata sticks. We’re professionals.” “Professionals in a bouncy castle? Hilarious,” Bill snorted. "Got the getaway stroller ready?" Molly sighed, “Alright, let’s swipe Santa’s stash before the tantrums start.”
created_at
"2026-05-10T11:53:05.605Z"
5/10/2026, 11:53:05 AM
model
"x-ai/grok-4.3-20260430"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
747
moderation_latency
(null)
generation_time
3455
tokens_prompt
77
tokens_completion
236
native_tokens_prompt
182
native_tokens_completion
195
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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"
service_tier
"default"
usage
0.0006478
router
(null)
provider_responses
0
endpoint_id
"45623cb8-18e5-4b32-8fc4-85d05439982d"
id
"b9caff7e-f156-c650-bf7a-a1377660763b"
is_byok
false
latency
266
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-1778413985-s90DKRkxrcgsKNiN1kXc"
session_id
(null)
api_type
"completions"
id
"gen-1778413985-8WMy2wDeAvYIQIFGR3ls"
upstream_id
"b9caff7e-f156-c650-bf7a-a1377660763b"
total_cost
0.0006478
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
136
50.10%
Dialogue to Total Word Ratio
Ratio: 80.88%, Deviation: 9.12%
neededClean
false
wordsTotal
136
wordsDialogue
110
25.0516%