NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8VVFTBEE4T5H99VZDN1TZ4
Run Details
Model:
Claude Sonnet 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 46s
Cost:
$0.191136
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 and Bill crouched behind the garden hedge, studying the birthday party with the intensity of generals surveying a contested battlefield. The target was a suburban backyard crawling with seven-year-olds, each one a tiny and unpredictable landmine wearing a party hat. A magnificent mountain of gift-wrapped presents sat completely unguarded on a folding table near the back fence, glittering under the afternoon sun like buried treasure that someone had inexplicably and generously wrapped in dinosaur paper. Bill adjusted his fake mustache, which was already peeling at the corners in the summer heat. He had insisted the disguise was necessary. Molly had insisted it was completely ridiculous. They had compromised, which meant Molly had simply stopped arguing. "We move in at cake time," Bill whispered. "Fine then. But that clown is watching everything," Molly hissed. The clown in question was enormous and deeply suspicious, possessed of the watchful eyes of a retired detective. He kept scanning the perimeter between balloon animals, which was genuinely unsettling for a man in a rainbow wig. Bill reached confidently into his jacket. "I brought snacks to distract him." Molly stared at the inadequate little bag of cheese crackers and said nothing, which frankly spoke volumes.
created_at
"2026-02-24T22:20:57.555Z"
2/24/2026, 10:20:57 PM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
976
moderation_latency
145
generation_time
105748
tokens_prompt
77
tokens_completion
3623
native_tokens_prompt
92
native_tokens_completion
12724
native_tokens_completion_images
(null)
native_tokens_reasoning
3289
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
0.191136
router
(null)
provider_responses
0
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
id
"0dc3ac0a-9bef-43b9-bf50-f7b23d188dc0"
is_byok
false
latency
975
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771971657-MrB4CTRlfDF6BiDshy8z"
upstream_id
"0dc3ac0a-9bef-43b9-bf50-f7b23d188dc0"
total_cost
0.191136
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 9.85%, Deviation: 0.15%
neededClean
false
wordsTotal
203
wordsDialogue
20
100.0000%