NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8WD712NHF2YJ5Q3XE53FAJ
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
13.6s
Cost:
$0.010310
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.6885%
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
Molly spread the crayon-drawn map across the dashboard and tapped it twice. "The party starts at two. We go in at two fifteen, right when the sugar hits." "Why two fifteen?" Bill asked, squinting at the map. "Because that's when they bring out the cake, Bill. Every kid in that bouncy castle will abandon their posts for a corner piece of sheet cake." "Their posts? They're six-year-olds, Molly." "Six-year-olds with zero loyalty and frosting addiction. That's what makes this window so beautiful." "And the presents?" "Stacked on a folding table by the back fence. I counted fourteen gift bags and at least three that are definitely LEGO." "How do you know they're LEGO?" "I know the shape of a LEGO box the way a jewel thief knows a Tiffany case. Trust me." "What about the parents?" "Half of them will be on their phones. The other half will be arguing about whose kid bit whose kid. Nobody's watching the table." "And our exit?" "Through the side gate. I already loosened the latch on my recon walk yesterday." "You did recon at a children's party?" "I wore a sun hat, Bill. I blended right in." Bill sighed. "This is the lowest we've sunk." "Lowest so far."
created_at
"2026-02-24T22:30:38.38Z"
2/24/2026, 10:30:38 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1499
moderation_latency
386
generation_time
13168
tokens_prompt
77
tokens_completion
364
native_tokens_prompt
92
native_tokens_completion
394
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
0.01031
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"befe910a-f5c4-4ca3-b522-47350467abbf"
is_byok
false
latency
1461
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771972238-OFbSAQGj8CtP53Pe3Cbz"
upstream_id
"befe910a-f5c4-4ca3-b522-47350467abbf"
total_cost
0.01031
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
205
100.00%
Dialogue to Total Word Ratio
Ratio: 90.00%, Deviation: 0.00%
neededClean
false
wordsTotal
210
wordsDialogue
189
99.6885%