NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8W9HH30C0343RYB5RM3ATQ
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
12.7s
Cost:
$0.010410
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.65%
Dialogue to Total Word Ratio
(details)
99.8232%
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
"So the party starts at two," Molly said, smoothing out a hand-drawn map on the dashboard. "We go in through the back gate at two-fifteen, when the magician starts his act." "A magician," Bill said. "Classy." "Every kid in that backyard will be watching some bloke pull a rabbit out of a hat. That gives us exactly twelve minutes to hit the present table." "And if someone spots us?" "We're caterers, Bill. That's why you're wearing the apron." Bill looked down at himself. "It says Kiss the Cook." "It was all they had at the thrift shop. Stay focused. The presents will be stacked on a folding table near the bouncy castle. We load them into the laundry bags, hop the fence, and we're gone before anyone notices." "What if there's a piñata situation? Those kids get feral around piñatas." "That's actually our backup distraction. I bought one shaped like a dinosaur. If things go sideways, we crack it open and run." "You're a genius, Molly." "I know. Now remember, no engaging with the children, no eating the cake, and absolutely no going in the bouncy castle." Bill's silence was deeply unconvincing. "Bill." "Fine," he said. "No bouncy castle."
created_at
"2026-02-24T22:28:38.062Z"
2/24/2026, 10:28:38 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1470
moderation_latency
220
generation_time
12434
tokens_prompt
77
tokens_completion
385
native_tokens_prompt
92
native_tokens_completion
398
native_tokens_completion_images
(null)
native_tokens_reasoning
71
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.01041
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"e401d245-8252-4c7c-a639-c81cb2eaf528"
is_byok
false
latency
1433
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771972118-YbLImDmUo3bDXtTCVCHa"
upstream_id
"e401d245-8252-4c7c-a639-c81cb2eaf528"
total_cost
0.01041
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
199
99.65%
Dialogue to Total Word Ratio
Ratio: 87.56%, Deviation: 2.44%
neededClean
false
wordsTotal
201
wordsDialogue
176
99.8232%