NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-12-01KKHYXSBECQGD0VFPBWYDNF5J
Run Details
Model:
Grok 4.20 (Beta, Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
40.5s
Cost:
$0.052896
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
82.08%
Dialogue to Total Word Ratio
(details)
86.2796%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 back room of their rundown safehouse, Molly and Bill sat in their dimly lit apartment plotting their most unusual caper yet. Molly spread out the party details on the table, her eyes gleaming as she pointed at the birthday cake picture while Bill looked uncomfortable. "This is the perfect target Bill. A children's party full of presents. We hit it hard and fast," Molly said. Bill shifted in his seat, clearly having second thoughts about their latest scheme. "But it's kids. Do we really want to steal their joy?" Bill asked. Molly waved off his concerns with a dismissive gesture. "Joy is overrated. Think of the profit from all those new toys," Molly replied. The male thief rubbed his chin thoughtfully. "How do we get in without being noticed?" Bill wondered. She smiled confidently at him. "We disguise as party entertainers. You as a clown and me as a magician. While you distract them I'll steal everything," she explained. He raised an eyebrow in skepticism. "What about escape?" he questioned. "The bouncy castle is our ticket out. Bounce right over the hedge," Molly answered. Finally convinced despite his many doubts, Bill stood up ready for action with a reluctant grin. "Sounds crazy but let's do it," he concluded.
created_at
"2026-03-12T21:23:30.291Z"
3/12/2026, 9:23:30 PM
model
"x-ai/grok-4.20-beta-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
39632
moderation_latency
(null)
generation_time
40431
tokens_prompt
77
tokens_completion
310
native_tokens_prompt
184
native_tokens_completion
8793
native_tokens_completion_images
0
native_tokens_reasoning
8535
native_tokens_cached
128
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.0528956
router
(null)
provider_responses
0
endpoint_id
"33f49f24-a0de-4dcf-872d-ca514e83fbae"
id
"35a59e7c-7961-3d09-4a1d-9c30ef9abd7f"
is_byok
false
latency
260
model_permaslug
"x-ai/grok-4.20-beta-20260309"
provider_name
"xAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773350610-drTmWMZ8QFBSBurC3K2R"
upstream_id
"35a59e7c-7961-3d09-4a1d-9c30ef9abd7f"
total_cost
0.0528956
cache_discount
0.0002304
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
210
82.08%
Dialogue to Total Word Ratio
Ratio: 43.33%, Deviation: 6.67%
neededClean
false
wordsTotal
210
wordsDialogue
91
86.2796%