NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-12-01KKHZ3FYB83C3YQ4N7P5F6K6K
Run Details
Model:
Grok 4.20 (Beta, Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
33.9s
Cost:
$0.041628
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
95.09%
Dialogue to Total Word Ratio
(details)
92.7869%
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
Bill said, "Molly, let's go over the plan one more time. We're breaking into that children's birthday party to steal all the presents. It's going to be our biggest score yet. You create a distraction by pretending to be the balloon animal maker while I sneak the gifts out the back door into our getaway van." "No, Bill, that's too obvious. The parents will notice a strange clown stealing toys. We should both go in as the surprise guests from the rental company. Act like we're delivering more presents but actually taking them all. During the magic show or whatever they have, the kids will be focused elsewhere," Molly replied. "You're right. We'll wear those silly hats and mingle. Then when the cake comes out, boom, we grab the pile and run. But what if the kids see us?" Bill responded. "We tell them it's part of the game, like a treasure hunt but for the adults. They'll buy it. Just don't drop any of the big boxes or the gig is up," said Molly. "Perfect. This will be hilarious. Thieves at a kids party. Who would suspect?" Bill added.
created_at
"2026-03-12T21:26:37.264Z"
3/12/2026, 9:26:37 PM
model
"x-ai/grok-4.20-beta-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
32993
moderation_latency
(null)
generation_time
33541
tokens_prompt
77
tokens_completion
266
native_tokens_prompt
184
native_tokens_completion
6915
native_tokens_completion_images
0
native_tokens_reasoning
6686
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
0.0416276
router
(null)
provider_responses
0
endpoint_id
"33f49f24-a0de-4dcf-872d-ca514e83fbae"
id
"3c55c398-b403-8835-fc87-cd5e1fc13e0b"
is_byok
false
latency
294
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-1773350797-l7rQ8DL82Be2TTBrPua7"
upstream_id
"3c55c398-b403-8835-fc87-cd5e1fc13e0b"
total_cost
0.0416276
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
190
95.09%
Dialogue to Total Word Ratio
Ratio: 94.74%, Deviation: 4.74%
neededClean
false
wordsTotal
190
wordsDialogue
180
92.7869%