NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCR3KGZ3ZZVWSJQCR4A4MV6
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.8s
Cost:
$0.012790
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
95.89%
Dialogue to Total Word Ratio
(details)
97.9349%
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 birthday boy's name is Terrance. He's turning seven." "Seven," Bill repeated. "Molly, we did the Antwerp diamond exchange." "And now we're doing Terrance." "Why?" "Because his father is a hedge fund manager who buys apologies instead of raising him. Do you know what's in that living room? A Nintendo Switch. Three of them. A remote-control helicopter that costs more than my car." "Your car is a 1994 Corolla." "Which is precisely my point." Bill sighed. "How do we get in?" "You're the entertainment." "Absolutely not." "There's a costume in the boot." "Molly." "It's a bear." "What kind of bear?" "The friendly kind. Vaguely. One eye is somewhat wrong." "And what are you doing while I'm being mauled by seven-year-olds?" "Balloons. Nobody watches the balloon lady. It's the perfect cover. I'll stage them by the patio door, you keep the little monsters distracted, and by four o'clock we're eating cake in a Travelodge." "And if a child asks me for a hug?" "Then you hug the child, Bill. You're a bear. Bears hug." "Bears maul." "Not this one. This one has a job to do." Bill stared at the house. "I want half the helicopter."
created_at
"2026-07-25T13:40:48.807Z"
7/25/2026, 1:40:48 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2531
moderation_latency
(null)
generation_time
9718
tokens_prompt
75
tokens_completion
344
native_tokens_prompt
93
native_tokens_completion
493
native_tokens_completion_images
(null)
native_tokens_reasoning
39
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
0.01279
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsUDygkeFyVb4dGjvFR"
is_byok
false
latency
1539
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-1784986848-EhQLdXtqfKeFCR5qwk6U"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986848-bePkLGwNulvol5PuinRo"
upstream_id
"msg_011CdNsUDygkeFyVb4dGjvFR"
total_cost
0.01279
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
198
95.89%
Dialogue to Total Word Ratio
Ratio: 94.53%, Deviation: 4.53%
neededClean
false
wordsTotal
201
wordsDialogue
190
97.9349%