NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8TVJ8Z7G7X3EE8BT1PBKWR
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
12.2s
Cost:
$0.011035
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
85.90%
Dialogue to Total Word Ratio
(details)
80.5265%
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, here's the layout. Bouncy castle on the left, face painting station on the right, and the present table is dead center by the inflatable dinosaur." "Why is there always an inflatable dinosaur?" "Focus, Bill. We go in through the back gate at exactly two fifteen, right when the clown starts his balloon animals. Every kid in that yard will be hypnotized." "I don't like clowns, Molly." "Nobody likes clowns. That's irrelevant. You'll be wearing the caterer's uniform I swiped from the van. You walk in carrying the fake cake, set it on the table, and while every parent is asking where the cake came from, I load the presents into the laundry bags." "What if a kid sees me?" "You offer them a juice box. Kids are powerless against juice boxes. It's basically a bribe they can drink." "This feels low, Molly. Robbing children." "We're not robbing children. We're robbing their parents, who frankly spent way too much at that toy store. We're correcting the economy, Bill." "That's not how economies work." "Do you want your cut or do you want to lecture me about macroeconomics?" Bill sighed and picked up the caterer's hat. "What flavor is the fake cake?" "It's not real, Bill." "It could still be a flavor, Molly."
created_at
"2026-02-24T22:03:31.494Z"
2/24/2026, 10:03:31 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1993
moderation_latency
168
generation_time
11938
tokens_prompt
77
tokens_completion
407
native_tokens_prompt
92
native_tokens_completion
423
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
0.011035
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"591f8f7c-0b11-48ff-bfa5-c7f7e9897fea"
is_byok
false
latency
1954
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771970611-r2hFlLA9qkLS4RdAymcS"
upstream_id
"591f8f7c-0b11-48ff-bfa5-c7f7e9897fea"
total_cost
0.011035
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
75.16%
Matches word count
n/a
neededClean
false
words
213
85.90%
Dialogue to Total Word Ratio
Ratio: 96.24%, Deviation: 6.24%
neededClean
false
wordsTotal
213
wordsDialogue
205
80.5265%