NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ915399QRXZYEMHYN9W4VK
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
7.3s
Cost:
$0.004695
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
99.94%
Dialogue to Total Word Ratio
(details)
95.2108%
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 pressed her back against the brick wall and unrolled a crayon drawing she'd stolen from a kindergartner's backpack. It was supposed to be the floor plan of the venue. "This is a rectangle with a dog in it," Bill whispered. "That's the bouncy castle." "That's a dog, Molly." She tapped the paper with authority. "We go in through the side entrance during the musical chairs chaos. Everyone looks left during musical chairs." Bill peered around the corner at the explosion of balloons and streamers. A clown was making an obscene amount of noise with a bicycle horn. "There are forty seven children in there," he said gravely. "Forty eight. The birthday kid counts double." "That's not a rule." "It's my rule." She zipped up her black turtleneck. "We grab the presents, we're out before cake. Nobody cries." "Somebody is absolutely going to cry." "Bill." "Multiple somebodies." Molly stuffed the crayon map into her pocket and looked him dead in the eye. "We are professionals. We have trained for this exact scenario." Bill stared back at her. "We have never trained for anything remotely like this scenario." "Semantics. Let's move."
created_at
"2026-02-18T02:25:02.431965+00:00"
2/18/2026, 2:25:02 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
602
moderation_latency
125
generation_time
6873
tokens_prompt
77
tokens_completion
310
native_tokens_prompt
75
native_tokens_completion
298
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
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
"stop"
usage
0.004695
router
(null)
provider_responses
0
id
"61083c7e-fea9-45bd-84a8-c8d62ca55e64"
status
200
is_byok
false
latency
602
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381495-5zwffiZwOhSQDyoS9idI"
upstream_id
"61083c7e-fea9-45bd-84a8-c8d62ca55e64"
total_cost
0.004695
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
190
99.94%
Dialogue to Total Word Ratio
Ratio: 51.58%, Deviation: 1.58%
neededClean
false
wordsTotal
190
wordsDialogue
98
95.2108%