NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8W02ENWHQK6T5T7FPGT9Y4
Run Details
Model:
Claude Sonnet 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 43s
Cost:
$0.156501
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
98.8120%
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 unfolded the hand-drawn blueprint across the dashboard and smoothed out the creases with her palm. It smelled faintly of cheese crackers. "The party starts at noon," she said. "We go in at cake time." Bill peered down at the blueprint. Several of the rooms had been labeled with stickers of cartoon dinosaurs. "Where exactly did you get this?" "Made it myself. Now pay attention." "Did you draw these dinosaurs?" "They're landmarks, Bill. Focus." He leaned closer, scratching the back of his neck. Outside, a minivan rolled slowly past with three balloons tied to the antenna. "What's our exit strategy?" he asked. "Through the garden. All gifts go in the laundry bags." Bill shifted uncomfortably in his seat. "These are children's presents, Molly." "Expensive children's presents. The birthday kid's dad is a hedge fund manager." "That does change things slightly." "It changes everything." She tapped the blueprint with authority. "The clown performs at one fifteen. That's our forty-five second window of total chaos." Bill stroked his mustache. He always stroked his mustache when logic was beating him senseless. "Fine," he said. "But I'm not wearing the elf costume." "You're wearing the elf costume."
created_at
"2026-02-24T22:23:27.71Z"
2/24/2026, 10:23:27 PM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
678
moderation_latency
201
generation_time
102605
tokens_prompt
77
tokens_completion
1088
native_tokens_prompt
92
native_tokens_completion
10415
native_tokens_completion_images
(null)
native_tokens_reasoning
760
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
0.156501
router
(null)
provider_responses
0
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
id
"d5e74708-8649-49ec-884a-a4ff6413f9db"
is_byok
false
latency
676
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771971807-UdKYI0QdUQtBAtnDoVXS"
upstream_id
"d5e74708-8649-49ec-884a-a4ff6413f9db"
total_cost
0.156501
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
193
100.00%
Dialogue to Total Word Ratio
Ratio: 50.77%, Deviation: 0.77%
neededClean
false
wordsTotal
195
wordsDialogue
99
98.8120%