NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPX1A2H0GTENA619HH5VYT
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.9s
Cost:
$0.012540
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.75%
Dialogue to Total Word Ratio
(details)
99.8678%
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
"So we're clear," Molly said. "You're the clown." "Why am I the clown?" "Because you have the face for it." "That's not a compliment." "It's not an insult either. Balloon animals, Bill. Can you make a balloon animal?" "I can make a balloon." "That's not an animal." "It's a snake." "Fine. You do snakes. I'll be the aunt nobody remembers inviting." "There's always one." "There's always three. That's why it works." Molly tapped the crayon map. "Gift table's here, by the piƱata. Twenty-two kids, sugar-blind by two o'clock." "And the parents?" "Wine." "All of them?" "It's a seven-year-old's birthday, Bill. They'll be at the wine like gulls at a chip." "I don't like it. Stealing from children." "You robbed a hospice." "That was a misunderstanding. I thought it was a hospital." "How is that better?" "Hospitals have insurance." Bill folded his arms. "What if a kid cries?" "Then you make a snake." "And if that doesn't work?" "Make two snakes." "Molly." "They're presents, Bill. Nobody remembers what they got when they were seven. We're doing them a favour. Building character." "You're a monster." "I'm a redistributor." She stood, straightening her cardigan. "Now put the nose on. We've got a party to attend."
created_at
"2026-07-25T13:19:44.968Z"
7/25/2026, 1:19:44 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1680
moderation_latency
(null)
generation_time
10765
tokens_prompt
75
tokens_completion
325
native_tokens_prompt
93
native_tokens_completion
483
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.01254
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqs4YZs3jguuy3LJaih"
is_byok
false
latency
1680
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-1784985584-7d2zsANz36N4EG8kbOPH"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985584-BF0UlmQpAB6G9wSqntnz"
upstream_id
"msg_011CdNqs4YZs3jguuy3LJaih"
total_cost
0.01254
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
99.98%
Matches word count
n/a
neededClean
false
words
202
99.75%
Dialogue to Total Word Ratio
Ratio: 92.23%, Deviation: 2.23%
neededClean
false
wordsTotal
206
wordsDialogue
190
99.8678%