NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8W47GZCTZ4QS2VTAPVPW07
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.0s
Cost:
$0.010335
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.80%
Dialogue to Total Word Ratio
(details)
99.8914%
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
"Alright, Bill, run me through the layout one more time," Molly said, spreading a crayon drawing across the dashboard. "So, the bouncy castle is here, which gives us cover from the north. The presents are stacked on a folding table near the back fence, right next to the face-painting station." "Security?" "One dad in cargo shorts. He's on grill duty, though, so he's distracted. The real threat is the birthday boy's grandmother. She's got eyes like a hawk and she's stationed near the gift table." "What's our window?" "Musical chairs. When that kicks off, every adult within fifty yards is going to be settling disputes and wiping tears. It's pure chaos, Molly. Beautiful, screaming chaos." "And the getaway?" "We go out through the side gate into the alley. I've got the minivan running. I slapped a magnetic sign on the side that says Party Supplies Express, so we blend right in." "What if a kid sees us?" "I brought fake mustaches." "Bill, that won't fool a child." "It won't fool anyone, Molly, but it'll confuse them long enough for us to clear the fence." She folded the crayon map and sighed. "This is either genius or our lowest moment." "Why not both?"
created_at
"2026-02-24T22:25:43.976Z"
2/24/2026, 10:25:43 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1535
moderation_latency
184
generation_time
10775
tokens_prompt
77
tokens_completion
388
native_tokens_prompt
92
native_tokens_completion
395
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
0.010335
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"453e5e89-9366-4ab8-921d-668c39df6329"
is_byok
false
latency
1489
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771971943-yZQEgkQMInXw6zVsfHxf"
upstream_id
"453e5e89-9366-4ab8-921d-668c39df6329"
total_cost
0.010335
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
99.80%
Dialogue to Total Word Ratio
Ratio: 92.12%, Deviation: 2.12%
neededClean
false
wordsTotal
203
wordsDialogue
187
99.8914%