NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCQVSQPHTNPXWAR19BF4VW6
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.8s
Cost:
$0.018290
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
96.60%
Dialogue to Total Word Ratio
(details)
96.2931%
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 blueprint across the van's hood, smoothing the creases with the reverence of a surgeon unfolding a patient. It was, technically, a hand-drawn map of the Pemberton backyard, rendered in crayon because that was all Bill had found in the glovebox. The bouncy castle was labeled OBSTACLE. The piƱata was labeled OPPORTUNITY. Bill studied it while eating a sausage roll, dropping flakes of pastry onto the parking lot like a man leaving a trail for his own rescue. He tapped the northeast corner, where Molly had drawn a lopsided figure in enormous shoes. "The clown's the weak link," he said. Molly nodded. Clowns were always the weak link. Underpaid, overheated, spiritually hollowed out by decades of unrequited laughter. A clown could be bought for forty pounds and a compliment. The presents, she explained, would be stacked on the trestle table beneath the banner, guarded by nothing more formidable than a grandmother with poor depth perception. Twenty-two children, one exhausted father, and a magician arriving at three. They would enter at two-fifty, disguised as the magician's assistants, and depart with a wheelbarrow of loot before the first rabbit emerged. "Balloons," Bill said. "Everyone trusts a man with balloons." Molly folded the map. It was almost too easy.
created_at
"2026-07-25T13:36:33.022Z"
7/25/2026, 1:36:33 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3864
moderation_latency
(null)
generation_time
12714
tokens_prompt
75
tokens_completion
396
native_tokens_prompt
93
native_tokens_completion
713
native_tokens_completion_images
(null)
native_tokens_reasoning
68
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
0.01829
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNs9N74J1n9SbuxWHeP6"
is_byok
false
latency
1222
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-1784986593-SaOjp5eh4taD7msKRKb4"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986593-GPxC7uPUnuYF5S7MU0GX"
upstream_id
"msg_011CdNs9N74J1n9SbuxWHeP6"
total_cost
0.01829
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
96.60%
Dialogue to Total Word Ratio
Ratio: 5.69%, Deviation: 4.31%
neededClean
false
wordsTotal
211
wordsDialogue
12
96.2931%