NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCR6SK3SYFE6EN3KXPP7S9F
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.8s
Cost:
$0.016140
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.3540%
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 blueprints across the hood of the van, weighting each corner with a half-eaten juice box she had confiscated from the recycling bin at the community center. The layout of the Pemberton back garden was crude but adequate: trestle table, piƱata, gazebo, and, glittering at the far end like the vault of a small Swiss bank, the present pile. She had been surveilling for six days. She knew the caterer's schedule, the grandmother's nap window, and the precise minute at which forty children would be simultaneously distracted by cake. Bill, meanwhile, had spent those six days learning to inflate balloon animals, and had produced only one recognizable species, which he insisted was an eel. "The clown is the weak link," Molly said, tapping the gazebo. Bill lowered his eel. "I hate clowns." "Then hate him quietly, from inside the bouncy castle." He nodded slowly, as though this were reasonable, which in the context of their partnership it was. Molly rolled the blueprints, tucked them into a Peppa Pig backpack, and checked her watch. Twenty-two minutes until the pony arrived. Bill's eel deflated with a long, mournful whistle. Neither of them acknowledged it.
created_at
"2026-07-25T13:42:33.323Z"
7/25/2026, 1:42:33 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4768
moderation_latency
(null)
generation_time
11650
tokens_prompt
75
tokens_completion
390
native_tokens_prompt
93
native_tokens_completion
627
native_tokens_completion_images
(null)
native_tokens_reasoning
89
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
0.01614
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsbwrYt7VcCSyetxN4H"
is_byok
false
latency
1494
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-1784986953-sAxMF9h6dSTEAdBh9oX4"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986953-fSykCiTAvmMECRp9ENdQ"
upstream_id
"msg_011CdNsbwrYt7VcCSyetxN4H"
total_cost
0.01614
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
194
100.00%
Dialogue to Total Word Ratio
Ratio: 9.18%, Deviation: 0.82%
neededClean
false
wordsTotal
196
wordsDialogue
18
99.3540%