NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRN47XD7GDSAM8VTRSAVB9
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.4s
Cost:
$0.013840
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
77.23%
Dialogue to Total Word Ratio
(details)
87.9735%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"Right," said Molly. "The target: Tilly Braithwaite, age six. Theme: unicorns." "I've got the van." "You've got a van?" "I've got *access* to a van. Ice cream van. Bit of a queue situation, potentially." "Bill, we're stealing presents, not selling ninety-nines." "That's the genius. Kids come to us. We drive off with the kids' presents while they're distracted by soft-serve." "The presents will be in the house." "Ah." "On a table. Behind a banner that says 'Tilly Is Six.'" "So we go in the back." "There's a bouncy castle in the back." "I love a bouncy castle." "You will not be bouncing." "I might bounce a bit. Professionally. For cover." "Bill." "What's the plan then, brains?" "You're the entertainment. Barry the Balloon Man cancelled this morning." "Barry cancelled? Barry's got a beautiful reputation—" "Barry got a flat tyre because somebody let his tyres down." "That somebody sounds thorough." "You go in with a bag of balloons. You do twenty minutes of twisting. Parents film it, everyone's charmed, nobody watches the present table." "And you?" "I'm Auntie Deborah. Nobody questions an Auntie Deborah." "Can I do the sausage dog?" "You can do the sausage dog." "Molly," said Bill, misty-eyed. "This is why I love working with you."
created_at
"2026-07-25T13:50:22.98Z"
7/25/2026, 1:50:22 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2378
moderation_latency
(null)
generation_time
11335
tokens_prompt
75
tokens_completion
351
native_tokens_prompt
93
native_tokens_completion
535
native_tokens_completion_images
(null)
native_tokens_reasoning
19
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
0.01384
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNtCYnT1yFyjqxva1TgD"
is_byok
false
latency
1198
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-1784987422-sFZzt81jH5rfqtYAshlm"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987422-UvNyKlY8ZryUqFEYFVGp"
upstream_id
"msg_011CdNtCYnT1yFyjqxva1TgD"
total_cost
0.01384
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
77.23%
Dialogue to Total Word Ratio
Ratio: 97.13%, Deviation: 7.13%
neededClean
false
wordsTotal
209
wordsDialogue
203
87.9735%