NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRHQW0F3TW04G8TX8SKXQ8
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.7s
Cost:
$0.012815
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
88.91%
Dialogue to Total Word Ratio
(details)
92.4498%
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 Fairbanks residence. Fourteen children, one bouncy castle, and forty-odd presents just sitting there in a pile." "I don't like it." "You said that about the pet shop." "And I was right. I still can't hear out of this ear because of that cockatoo." "Bill. There's no alarm. There's no dog. There's a woman named Deborah handing out slices of Colin the Caterpillar." "There's fourteen children." "Children are not a security system." "Children are the *ultimate* security system. They're small, they're everywhere, and they have no respect for the social contract. One of them bit my cousin at a christening. Straight through the trousers." "We'll be in and out in ninety seconds." "And how are we getting in?" "You'll be the entertainment. Clowns go unquestioned." "Absolutely not." "I've bought the wig." "Molly—" "It's ginger. It's very expressive." "What are you doing while I'm being *expressive*?" "Loading the van. You keep them occupied with balloon animals." "I can do a snake." "A snake is a balloon, Bill." "It's a very *convincing* snake." Molly sighed and folded the blueprint. "Fine. Do the snake. Just don't let Deborah near the gift table."
created_at
"2026-07-25T13:48:32.01Z"
7/25/2026, 1:48:32 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3137
moderation_latency
(null)
generation_time
9558
tokens_prompt
75
tokens_completion
360
native_tokens_prompt
93
native_tokens_completion
494
native_tokens_completion_images
(null)
native_tokens_reasoning
49
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
0.012815
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNt4NVMLceSmBtzD17R7"
is_byok
false
latency
1214
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-1784987312-fERWah3sLxOzIlMcz3fP"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987312-BqbqDJDGsEvVjd87WyoI"
upstream_id
"msg_011CdNt4NVMLceSmBtzD17R7"
total_cost
0.012815
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
192
88.91%
Dialogue to Total Word Ratio
Ratio: 95.85%, Deviation: 5.85%
neededClean
false
wordsTotal
193
wordsDialogue
185
92.4498%