NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8VVMBQ89WK8M02ZVE34YPD
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.6s
Cost:
$0.010860
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
97.9933%
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
"Right," Molly said, unrolling a crayon-drawn map across the dashboard. "The party starts at two. We go in through the back gate." "The back gate with the squeaky latch?" Bill asked. "We'll use WD-40." "On a child's gate. We're greasing a child's gate, Molly." "Do you want the presents or not?" "I do want the presents." "Then stop questioning my methods. Now, the gifts will be stacked on a folding table near the bouncy castle. You grab everything you can carry while I create a distraction." "What kind of distraction?" "I'm going to challenge the birthday boy's father to a limbo contest." "You can't even touch your toes." "Exactly. It'll be mesmerizing. Everyone will watch. Meanwhile, you load the van." "What if a kid sees me?" "Tell them you're from the valet service." "For presents?" "Children are stupid, Bill. That's why they still believe in Santa Claus, and that, frankly, is the whole reason we're in business." "Fair point. What's our exit strategy?" "We drive away." "That's it?" "It's a cul-de-sac in the suburbs, not the Louvre. We drive away, Bill." Bill folded his arms and nodded slowly. "I love this plan."
created_at
"2026-02-24T22:21:02.208Z"
2/24/2026, 10:21:02 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2115
moderation_latency
180
generation_time
11301
tokens_prompt
77
tokens_completion
390
native_tokens_prompt
92
native_tokens_completion
416
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
0.01086
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"cdabef98-33f5-4a35-83ea-edd072ce675b"
is_byok
false
latency
2079
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771971662-c6DUb8u1btJ83by3lgcf"
upstream_id
"cdabef98-33f5-4a35-83ea-edd072ce675b"
total_cost
0.01086
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
192
100.00%
Dialogue to Total Word Ratio
Ratio: 90.31%, Deviation: 0.31%
neededClean
false
wordsTotal
196
wordsDialogue
177
97.9933%