NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8X6Q03209GJZZ10481D1Z1
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
55.6s
Cost:
$0.124785
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.92%
Dialogue to Total Word Ratio
(details)
99.9575%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 blueprint across the hood of their rusted van, weighing down one corner with a juice box she'd stolen from a gas station earlier that morning. The diagram showed the Patterson backyard in extraordinary detail, complete with crayon-colored annotations marking the bounce house, the face-painting station, and most critically, the present table. Bill squinted at the map and turned it sideways. "Why is there a moat?" "That's the slip-and-slide. Focus." She had been casing the Patterson residence for three weeks, posing as a dog walker despite not owning a dog. The neighbors had grown suspicious, but only because she kept walking a stuffed animal on a leash and photographing the fence line. The plan was elegant in its simplicity. Bill would create a diversion dressed as a clown, which required no costume change according to Molly. While the children swarmed him, she would load the gifts into large trash bags and escape through a gap in the fence. "What if the kids don't like clowns?" Bill asked nervously. "Nobody likes clowns. That's the point." Bill nodded slowly, the terrible logic settling over him like a warm, criminal blanket. They synchronized their watches, both of which were broken.
created_at
"2026-02-24T22:44:33.929Z"
2/24/2026, 10:44:33 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1539
moderation_latency
202
generation_time
55359
tokens_prompt
77
tokens_completion
1170
native_tokens_prompt
92
native_tokens_completion
4973
native_tokens_completion_images
(null)
native_tokens_reasoning
848
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
0.124785
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"8ba7a78a-6b6f-4dcc-8407-41d22008a397"
is_byok
false
latency
1498
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771973073-U4hE0m9OC2MfU4sNJEQ9"
upstream_id
"8ba7a78a-6b6f-4dcc-8407-41d22008a397"
total_cost
0.124785
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
99.92%
Dialogue to Total Word Ratio
Ratio: 11.71%, Deviation: 1.71%
neededClean
false
wordsTotal
205
wordsDialogue
24
99.9575%