NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8TKBSG06BTM72KSRJMJJG8
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
23.9s
Cost:
$0.037335
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
99.9561%
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 sedan, smoothing out the crayon marks with her fingertips. The blueprint had cost them two juice boxes and a firm promise to return Tommy Henderson's stuffed rabbit by Thursday. Bill squinted at it, rotating the paper three times before accepting he was holding it upside down. The target was simple enough. Fourteen children, one bouncy castle, and a mountain of presents stacked beside a table drowning in frosting. Security consisted of a golden retriever named Biscuit and a grandmother who fell asleep during every episode of Wheel of Fortune. "We go in through the backyard," Molly whispered. "During musical chairs." Bill nodded slowly, stroking his chin like a man who understood strategy, which he absolutely did not. His last heist had involved stealing a garden gnome, and he'd somehow returned home with two. "What about the clown?" he asked. Molly's eye twitched. She hadn't accounted for the clown. Nobody ever accounted for the clown. Those oversized shoes could cover ground faster than anyone expected, and their pockets were an unpredictable wilderness of handkerchiefs and balloon animals. She folded the map carefully. "We'll need a bigger bag."
created_at
"2026-02-24T21:59:03.022Z"
2/24/2026, 9:59:03 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1971
moderation_latency
165
generation_time
23295
tokens_prompt
77
tokens_completion
720
native_tokens_prompt
92
native_tokens_completion
1475
native_tokens_completion_images
(null)
native_tokens_reasoning
398
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
0.037335
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"b50046d1-3edf-4511-8b7c-8d55789a5a12"
is_byok
false
latency
1934
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771970343-Xq2gfT8jWu26tZC0am5Y"
upstream_id
"b50046d1-3edf-4511-8b7c-8d55789a5a12"
total_cost
0.037335
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
99.99%
Dialogue to Total Word Ratio
Ratio: 9.09%, Deviation: 0.91%
neededClean
false
wordsTotal
198
wordsDialogue
18
99.9561%