NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8VZJHRQN04SSJHAZ6HST8J
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.8s
Cost:
$0.010060
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
91.94%
Dialogue to Total Word Ratio
(details)
95.3247%
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 hand-drawn map across the hood of their dented minivan. It was covered in crayon and smelled faintly of grape juice. She had stolen it from the fridge of the birthday boy himself. "The bouncy castle is here," she said, tapping a purple blob. "That's our primary obstacle." Bill squinted at the map and turned it upside down. "Why is everything drawn in what appears to be dinosaur?" "The kid is six, Bill. Focus." She pulled out a pair of binoculars and nodded toward the backyard. "The presents are stacked on a folding table near the back fence. I count at least thirty gifts. Could be huge money." "Could also be thirty boxes of Legos," Bill muttered. "Legos have incredible resale value and you know it." He couldn't argue with that. He'd paid rent twice last year on Legos alone. "So what's the plan?" he asked. Molly grinned the way she always did before something went beautifully wrong. "We go in disguise. You're the clown." "Absolutely not." "You're the clown, Bill." He stared at her for a long moment, then sighed with his entire body. "I'm going to need a bigger nose."
created_at
"2026-02-24T22:23:11.425Z"
2/24/2026, 10:23:11 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1591
moderation_latency
136
generation_time
10631
tokens_prompt
77
tokens_completion
365
native_tokens_prompt
92
native_tokens_completion
384
native_tokens_completion_images
(null)
native_tokens_reasoning
69
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
0.01006
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"ad8ce13a-5d5e-4e97-8139-18b563a174c5"
is_byok
false
latency
1562
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771971791-aP7CsVf5SEh6OKFDPSeF"
upstream_id
"ad8ce13a-5d5e-4e97-8139-18b563a174c5"
total_cost
0.01006
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
194
91.94%
Dialogue to Total Word Ratio
Ratio: 44.62%, Deviation: 5.38%
neededClean
false
wordsTotal
195
wordsDialogue
87
95.3247%