NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPNJ16562E53093VB9H1CG
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.6s
Cost:
$0.011740
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 crayon-drawn map across the hood of the van. "Bounce house here. PiƱata there. Presents stacked on the folding table, guarded by nine-year-olds hopped up on Capri Sun." "I don't like it," Bill said. "You don't like anything." "I don't like *children*, Molly. They've got no code. They'll bite a man." "That's why you're wearing the clown suit." Bill stared at the crumpled costume in her lap. "Absolutely not." "Nobody questions a clown at a birthday party. You walk in, you honk the nose, you twist a balloon poodle, and you distract them while I load the loot into the bouncy castle." "Why the bouncy castle?" "Because it deflates, Bill. It becomes a bag. A big, festive bag." He rubbed his temples. "And the parents?" "Sheet cake. Once that cake comes out, the adults form a queue and lose all situational awareness. We've got ninety seconds." "What if somebody asks me to do a magic trick?" "Then do a magic trick." "I don't know any magic tricks!" "Make the presents disappear," Molly said, tossing him a red foam nose. "You've had thirty years of practice." Bill sighed, snapping the elastic behind his head. "If a toddler punches me, I'm punching back."
created_at
"2026-07-25T13:15:39.947Z"
7/25/2026, 1:15:39 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1460
moderation_latency
(null)
generation_time
9475
tokens_prompt
75
tokens_completion
307
native_tokens_prompt
93
native_tokens_completion
451
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
0.01174
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqZ1D95Hd6hY33DJ8Yw"
is_byok
false
latency
1460
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-1784985339-vDpL4lggOKyP4Sxl4Dc3"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985339-DilzmTFdDNGjsoNnn3kX"
upstream_id
"msg_011CdNqZ1D95Hd6hY33DJ8Yw"
total_cost
0.01174
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
99.92%
Matches word count
n/a
neededClean
false
words
203
0.00%
Dialogue to Total Word Ratio
Ratio: 79.13%, Deviation: 29.13%
neededClean
false
wordsTotal
206
wordsDialogue
163
49.9595%