NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8V033JWQB6HEK6G6HMRFCX
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
34.5s
Cost:
$0.086835
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9989%
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 spread the hand-drawn map across the hood of their rusted van, squinting at crayon-colored stick figures and what appeared to be a bouncy castle rendered in aggressive purple. Bill leaned over her shoulder, breathing heavily through his mouth like a man who had never encountered fresh air and found the whole concept suspicious. "So we go in through the back gate at three," Molly whispered. Bill nodded, adjusting his ski mask, which he had already put on despite the fact that they were parked outside a grocery store in broad daylight. Two elderly women had already called the police, but neither thief had noticed. The party was at the Henderson residence, a modest suburban home defended by nothing more than a picket fence and a golden retriever named Sprinkles. Molly had done reconnaissance for three days, which mostly involved eating ice cream in her car and watching six-year-olds practice soccer. "What about the clown?" Bill asked. "We neutralize the clown first." Bill swallowed hard. He had a terrible thing about clowns. Molly knew this perfectly well. She was already enjoying herself. The presents, wrapped in glittering paper and piled high on a folding table, would be theirs by sundown.
created_at
"2026-02-24T22:05:59.805Z"
2/24/2026, 10:05:59 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1636
moderation_latency
157
generation_time
34258
tokens_prompt
77
tokens_completion
1178
native_tokens_prompt
92
native_tokens_completion
3455
native_tokens_completion_images
(null)
native_tokens_reasoning
862
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
0.086835
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"d2562a51-4ec6-4cd4-b071-e74fc26e73cd"
is_byok
false
latency
1601
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771970759-XO5SnOejI75b42bvDcFg"
upstream_id
"d2562a51-4ec6-4cd4-b071-e74fc26e73cd"
total_cost
0.086835
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: 9.31%, Deviation: 0.69%
neededClean
false
wordsTotal
204
wordsDialogue
19
99.9989%