NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8W6VB6WSZ65990YCA42EC9
Run Details
Model:
Grok 4.3
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.8s
Cost:
$0.000690
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
63.88%
Dialogue to Total Word Ratio
(details)
31.9412%
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 crouched behind the hedge, her gloved fingers tracing the map of the backyard on crumpled paper while balloons bobbed in the distance. Bill slithered closer, his sneakers squeaking against damp grass. Their target was two blocks down, a clown-infested yard filled with oversized cakes and brightly wrapped boxes worth more than their last three jobs combined. "Molly, this is nuts," Bill whispered, "what if the parents catch us?" "Bill, they’ll be busy arguing over juice boxes, trust me." "Still feels like robbing toddlers." "Then call it a donation." She counted the seconds until the clown’s back was turned, her heart hammering like a tiny drum solo. Bill adjusted the black ski mask that made him look ridiculous, not menacing. They needed speed, silence, and zero fingerprints on any sticky lollipop residue. A balloon popped nearby, jolting them both. Molly nodded once, certain the gate would be unlocked and the presents stacked high near the trampoline. Bill exhaled slowly, already tasting victory cake crumbs.
created_at
"2026-05-10T12:01:20.749Z"
5/10/2026, 12:01:20 PM
model
"x-ai/grok-4.3-20260430"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
484
moderation_latency
(null)
generation_time
3663
tokens_prompt
77
tokens_completion
267
native_tokens_prompt
182
native_tokens_completion
212
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
0.0006903
router
(null)
provider_responses
0
endpoint_id
"45623cb8-18e5-4b32-8fc4-85d05439982d"
id
"1f2c797d-21f5-9a36-a4c5-ad6996bc5d79"
is_byok
false
latency
133
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-1778414480-IT5vJzxyl3PssUvnjt5U"
session_id
(null)
api_type
"completions"
id
"gen-1778414480-04RGZ09H0IMUwC65Qx5z"
upstream_id
"1f2c797d-21f5-9a36-a4c5-ad6996bc5d79"
total_cost
0.0006903
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
164
63.88%
Dialogue to Total Word Ratio
Ratio: 18.18%, Deviation: 8.18%
neededClean
false
wordsTotal
165
wordsDialogue
30
31.9412%