NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8WS5C317BTG24Y4XHR2G4Y
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 20s
Cost:
$0.185460
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
99.8674%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 pressed her face against the chain-link fence, watching six-year-olds tear across the backyard like sugared-up velociraptors. A mountain of wrapped presents glittered on a folding table near the bounce house. "There's our score," she whispered. "Has to be five hundred dollars on that table, easy." Bill raised his taped-together binoculars. "I count fifteen, maybe twenty boxes. Could be anything in there. LEGOs, gift cards, maybe one of those robot dogs that do backflips." "Robot dogs retail for eighty bucks. We grab everything and sort later." "What about the clown?" Bill asked, nodding toward a man in oversized shoes twisting balloon animals by the gate. "Clowns are wildly unpredictable. We avoid him entirely." "Agreed. I've had terrible experiences with clowns." Molly unrolled a hand-drawn blueprint on the hood of their dented minivan. She'd sketched the yard in crayon, which was all they could afford after the last job went sideways. "You slip in through the side gate during the piƱata. Every kid will be blindfolded or distracted by falling candy." "Brilliant," Bill said, grinning. "What's my disguise?" Molly reached into the backseat and produced a tiny princess tiara. "You cannot be serious." "Put it on, Bill."
created_at
"2026-02-24T22:37:09.899Z"
2/24/2026, 10:37:09 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1542
moderation_latency
157
generation_time
78957
tokens_prompt
77
tokens_completion
1144
native_tokens_prompt
92
native_tokens_completion
7400
native_tokens_completion_images
(null)
native_tokens_reasoning
810
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
0.18546
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"22cc6ab5-58e6-4d04-a141-d8ebaba21f3c"
is_byok
false
latency
1504
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771972629-g05c15ea5mk3j2NmrotZ"
upstream_id
"22cc6ab5-58e6-4d04-a141-d8ebaba21f3c"
total_cost
0.18546
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
196
99.99%
Dialogue to Total Word Ratio
Ratio: 49.01%, Deviation: 0.99%
neededClean
false
wordsTotal
202
wordsDialogue
99
99.8674%