NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRDJCH9TX6DHF87DZ00JY3
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.3s
Cost:
$0.016015
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
99.70%
Dialogue to Total Word Ratio
(details)
97.8425%
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, weighing down the corners with a half-eaten sausage roll and three party hats she'd stolen from a supermarket that morning. The house on Wisteria Lane had two exits, one nervous mother, and, according to the invitation Bill had liberated from a recycling bin, a bouncy castle arriving at half past two. "The clown's the weak link," she said. Bill studied the diagram of the garden, tracing the route from the trampoline to the gift table with a finger still faintly sticky from reconnaissance cupcakes. Fourteen children, all under the age of eight, all hopped up on cordial and unpredictable as weather. The presents would be stacked in the conservatory, unguarded, glittering in their wrapping like treasure in a very small, very pink cave. He frowned at the party hats. "I refuse to wear the elastic." Molly ignored him. She had already worked out the timing: enter during the musical chairs, when the adults were distracted and the shrieking reached its peak volume, then out through the side gate with the loot in a bin bag disguised as a piƱata. Simple. Elegant. Morally indefensible. "Nobody ever suspects the magician," she said, and pulled a wilted bouquet from her sleeve.
created_at
"2026-07-25T13:46:15.322Z"
7/25/2026, 1:46:15 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3861
moderation_latency
(null)
generation_time
11191
tokens_prompt
75
tokens_completion
390
native_tokens_prompt
93
native_tokens_completion
622
native_tokens_completion_images
(null)
native_tokens_reasoning
76
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
0.016015
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNstHvVJJdsmp4enEA4j"
is_byok
false
latency
1227
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-1784987175-L0VTZzc6Ej4KTAa8rAuO"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987175-HyikGvlJR1ecIwUpu7Wk"
upstream_id
"msg_011CdNstHvVJJdsmp4enEA4j"
total_cost
0.016015
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
95.99%
Matches word count
n/a
neededClean
false
words
208
99.70%
Dialogue to Total Word Ratio
Ratio: 7.66%, Deviation: 2.34%
neededClean
false
wordsTotal
209
wordsDialogue
16
97.8425%