NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRKXKAT1C5TQZNV8KA48NW
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
12.4s
Cost:
$0.014865
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
93.59%
Dialogue to Total Word Ratio
(details)
96.1532%
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 spread the blueprint across the hood of the van. It was a paper placemat from Chuck E. Cheese, crayoned in three colors. "The bouncy castle is here," she said, tapping a wobbly square. "Two exits, one clown, and eleven children under the age of seven." "Eleven?" Bill lowered his binoculars. "You said six." "I miscounted. There was a piƱata blocking my sightline." He wiped his palms on his jeans. Somewhere beyond the fence, a chorus of shrieking rose and fell like weather. "The presents are stacked on the folding table," Molly continued. "Sixteen boxes, minimum. One of them is shaped like a bicycle." "And the parents?" "Distracted. Cake comes out at four-fifteen. That's our window." "Molly." Bill's voice went thin. "There's a magician." "So?" "Magicians notice things. It's literally the job." She handed him a paper crown and a wrapped shoebox containing bricks. "You're Uncle Terry. You're late, you're divorced, and nobody will ask questions because everyone assumes somebody else invited you." "What's in the box?" "Disappointment." Bill settled the crown on his head, adjusted it, and squared his shoulders like a man walking into a courtroom. "For the record," he said, "this is the lowest we've ever gone." "Sixteen boxes, Bill." "Fine. Sixteen boxes."
created_at
"2026-07-25T13:49:43.412Z"
7/25/2026, 1:49:43 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5621
moderation_latency
(null)
generation_time
12236
tokens_prompt
75
tokens_completion
375
native_tokens_prompt
93
native_tokens_completion
576
native_tokens_completion_images
(null)
native_tokens_reasoning
43
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"end_turn"
service_tier
"default"
usage
0.014865
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNt9gkqkJygH4xDLsGGb"
is_byok
false
latency
2442
model_permaslug
"anthropic/claude-opus-5-20260723"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784987383-KAELHNZl1DKKhQxKdeee"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987383-WVoh3CZr5vIc9cNrq26d"
upstream_id
"msg_011CdNt9gkqkJygH4xDLsGGb"
total_cost
0.014865
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
206
93.59%
Dialogue to Total Word Ratio
Ratio: 55.07%, Deviation: 5.07%
neededClean
false
wordsTotal
207
wordsDialogue
114
96.1532%