NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPXH1MYS7YV858KHCMAVFP
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.6s
Cost:
$0.012140
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.6885%
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. "The bouncy castle is here. Presents pile up on the folding table, here, under the piñata." "A piñata," Bill said. "That's a hazard. Blindfolded child swinging a stick." "That's the diversion, Bill. Nobody looks at the table when candy hits the grass." "And the parents?" "Drinking wine out of plastic cups and pretending they like each other. We have eleven minutes." Bill frowned at the map. "What's this squiggle?" "Grandma. She sits by the gate. She'll offer you a butterscotch." "I take it?" "You take it, you thank her, you keep walking. Refuse and she remembers your face forever." "And the clown?" "There's no clown." "There's always a clown." "There's a magician named Marvelous Dennis. He does the linking rings, badly, and he's the only adult who'll be looking our direction." Bill sighed. "So we're stealing from six-year-olds." "We're stealing from a hedge fund manager who bought his son a diamond-studded scooter to spite his ex-wife. The presents are collateral." "Right." Bill straightened his clip-on tie. "And my cover?" "You're Marvelous Dennis's assistant." "I can't do magic, Molly." "Neither can Dennis. Grab the balloons."
created_at
"2026-07-25T13:20:01.084Z"
7/25/2026, 1:20:01 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1477
moderation_latency
(null)
generation_time
9458
tokens_prompt
75
tokens_completion
316
native_tokens_prompt
93
native_tokens_completion
467
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
0.01214
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqtGL1Pn2oGUhS6k7kj"
is_byok
false
latency
1477
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-1784985601-gy7tBm5wg6WH5eZryEjG"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985601-ir3QaEUxwZRB2XywSJ03"
upstream_id
"msg_011CdNqtGL1Pn2oGUhS6k7kj"
total_cost
0.01214
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
99.38%
Matches word count
n/a
neededClean
false
words
195
0.00%
Dialogue to Total Word Ratio
Ratio: 86.50%, Deviation: 36.50%
neededClean
false
wordsTotal
200
wordsDialogue
173
49.6885%