NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR9084GJT9Q5EV65RFG8K6AH
Run Details
Model:
Grok 4.3
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.8s
Cost:
$0.000765
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
2.01%
Matches word count
(details)
99.94%
Dialogue to Total Word Ratio
(details)
50.9778%
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
"Well this plan's a bloody stitch-up, Bill," she said, waving a crumpled map of the party venue. "It ain't a stitch-up, it's brilliant," he shot back, pointing at a balloon-shaped doodle he'd drawn. "The clowns are bringing the gifts through the side door, right? We hit 'em while everyone's screaming at the magician." "Brilliant? Half the kids'll still be there, tearing wrapping paper like locusts. We need a distraction bigger than your last job." "Which is why I nicked the bouncy castle remote. Inflate it to bursting point, kids swarm, adults panic, gifts unguarded. Easy pickings." "Easy? What if some toddler's got super-glue hands and won't let go of his scooter?" "Then we offer him choc buttons. Bribery works on everyone under five." "Until his mum clocks us swiping the good stuff. I'm not facing a nursery riot over Lego sets." "They're worth a fortune on the quiet market, Molly. One good score, and we retire to that alpaca farm you've always talked about." "Alpacas? While dodging five-year-olds armed with sticky fingers and half-eaten cake?"
created_at
"2026-05-10T13:11:57.21Z"
5/10/2026, 1:11:57 PM
model
"x-ai/grok-4.3-20260430"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
468
moderation_latency
(null)
generation_time
4685
tokens_prompt
77
tokens_completion
280
native_tokens_prompt
182
native_tokens_completion
242
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
0.0007653
router
(null)
provider_responses
0
endpoint_id
"45623cb8-18e5-4b32-8fc4-85d05439982d"
id
"761bfec4-63cf-9122-9bb9-864ec34f8440"
is_byok
false
latency
112
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-1778418717-uuGuGmMx1aKpYyuiM44E"
session_id
(null)
api_type
"completions"
id
"gen-1778418717-OtD8J85JyCMYmEOcGqCJ"
upstream_id
"761bfec4-63cf-9122-9bb9-864ec34f8440"
total_cost
0.0007653
cache_discount
0.0000672
upstream_inference_cost
0
provider_name
"xAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
2.01%
Matches word count
n/a
neededClean
false
words
175
99.94%
Dialogue to Total Word Ratio
Ratio: 88.46%, Deviation: 1.54%
neededClean
false
wordsTotal
182
wordsDialogue
161
50.9778%