NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-01-01KQHT4GQFQ1478FT8SG2R4B24
Run Details
Model:
Grok 4.20 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3m 15s
Cost:
$0.038098
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
92.54%
Dialogue to Total Word Ratio
(details)
96.2705%
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
Molly and Bill crouched behind a hedge near the noisy children's party filled with balloons, games and laughter. Their hearts raced with anticipation and guilt. "Bill, let's hit the party at three," Molly said. "You distract with magic, I grab the presents. Easy." Bill peeked over the leaves nervously. "But what if the kids cry or the parents call the cops on us, Molly?" he asked. Molly chuckled, pulling clown wigs from her backpack. "Stop worrying. We wear clown suits and blend in. Think of the money from selling those new bikes and toys." She handed him a red nose with an encouraging smile. Bill took it reluctantly looking quite unhappy about the whole thing. "This is insane. Stealing from children at their own party. But okay, if you say so." Molly grinned as she applied her makeup in preparation for the big event. "Exactly. And remember no one will suspect us because who would think thieves would be so heartless to take from kids." Bill sighed, adjusting his outfit with obvious reluctance showing on his face. "You have a point there. Let's go over the escape route one more time before we suit up for this crazy job."
created_at
"2026-05-01T13:02:35.253Z"
5/1/2026, 1:02:35 PM
model
"x-ai/grok-4.20-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
192897
moderation_latency
(null)
generation_time
195189
tokens_prompt
77
tokens_completion
925
native_tokens_prompt
184
native_tokens_completion
15201
native_tokens_completion_images
(null)
native_tokens_reasoning
14961
native_tokens_cached
128
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"
usage
0.0380981
router
(null)
provider_responses
0
endpoint_id
"3ecee37f-b217-4093-87fb-aaf0afe307af"
id
"6b0f1380-6bc6-9104-856b-c0cdb57d84a1"
is_byok
false
latency
103
model_permaslug
"x-ai/grok-4.20-20260309"
provider_name
"xAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777640555-0ReNqi7HMbagchsZJ3b4"
session_id
(null)
api_type
"completions"
id
"gen-1777640555-6ISW8LiT9metyKvHonMn"
upstream_id
"6b0f1380-6bc6-9104-856b-c0cdb57d84a1"
total_cost
0.0380981
cache_discount
0.0001344
upstream_inference_cost
0
provider_name
"xAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
199
92.54%
Dialogue to Total Word Ratio
Ratio: 55.28%, Deviation: 5.28%
neededClean
false
wordsTotal
199
wordsDialogue
110
96.2705%