NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8VYDDHC6QMH3A8KBQ9H4MM
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
40.9s
Cost:
$0.093610
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 spread the hand-drawn map across the hood of their dented minivan, weighing down one corner with a half-eaten burrito. The blueprint, if you could call crayon on construction paper that, showed the layout of the Henderson house in disturbing detail. She had spent three days befriending a six-year-old at the playground to get this intelligence, which she considered her finest undercover work to date. Bill squinted at the map, turning it sideways, then upside down. "That's either a swimming pool or a very large dog," he said. "It's the bounce house, you absolute walnut," Molly snapped. She tapped the garage entry point with a chewed fingernail. The party was scheduled for Saturday at two. They would arrive at one-thirty disguised as clowns, which Bill had protested on moral grounds, claiming clowns had enough reputational problems already. Molly had overruled him. Nobody questions a clown carrying oversized bags. It was practically expected. The present table, according to her tiny informant, would be positioned near the back door. Easy access. Quick exit. The only real obstacle was a golden retriever named Captain Sprinkles who apparently bit strangers. "We'll need extra cheese," Bill said gravely. Molly nodded slowly. They always needed cheese.
created_at
"2026-02-24T22:22:33.404Z"
2/24/2026, 10:22:33 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1930
moderation_latency
166
generation_time
40582
tokens_prompt
77
tokens_completion
1538
native_tokens_prompt
92
native_tokens_completion
3726
native_tokens_completion_images
(null)
native_tokens_reasoning
1206
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
0.09361
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"b33735c7-c546-4a23-9b68-7297a7f60b25"
is_byok
false
latency
1897
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771971753-VIUlaKE0aGN96pcjlhR5"
upstream_id
"b33735c7-c546-4a23-9b68-7297a7f60b25"
total_cost
0.09361
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: 10.24%, Deviation: 0.24%
neededClean
false
wordsTotal
205
wordsDialogue
21
100.0000%