NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8VCE8G4B36N5EJKDA81GBV
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.9s
Cost:
$0.010510
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
97.57%
Dialogue to Total Word Ratio
(details)
98.6571%
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 rusty van. It was covered in crayon, because she had stolen it from a kindergartner. "The party starts at two," she said, tapping a wobbly rectangle labeled BOUNCY HOUSE. "That gives us a narrow window while the kids are distracted by the clown." Bill squinted at the map and turned it upside down. "I hate clowns." "Everyone hates clowns, Bill. That's why he's perfect cover." He scratched his chin nervously. The last job had gone sideways when Bill developed a sudden moral crisis inside a Chuck E. Cheese. Molly was not about to let that happen again. "What about the parents?" he asked. "There's always some dad hovering by the gift table like a security guard." "Wine," Molly said confidently. "Susan's mother puts out sangria at every party. By two-fifteen, every adult in that backyard will be arguing about school rezoning. Nobody will notice us." Bill pulled on his black ski mask, then immediately removed it. "It's eighty degrees outside. I'll pass out." "Fine. Wear the birthday hat I packed instead. We blend in." "We're thirty-seven years old, Molly." "Thirty-seven-year-olds love birthdays, Bill. Stop overthinking this."
created_at
"2026-02-24T22:12:44.443Z"
2/24/2026, 10:12:44 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1476
moderation_latency
238
generation_time
11591
tokens_prompt
77
tokens_completion
390
native_tokens_prompt
92
native_tokens_completion
402
native_tokens_completion_images
(null)
native_tokens_reasoning
72
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
0.01051
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"6c856cfd-7bdc-497f-8df0-a1c98206fdd3"
is_byok
false
latency
1445
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771971164-xDs31KeKZn9bS0Y5WBYO"
upstream_id
"6c856cfd-7bdc-497f-8df0-a1c98206fdd3"
total_cost
0.01051
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
196
97.57%
Dialogue to Total Word Ratio
Ratio: 53.96%, Deviation: 3.96%
neededClean
false
wordsTotal
202
wordsDialogue
109
98.6571%