NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8TWRQ26ESWJKANCWZR8YB2
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
13.1s
Cost:
$0.010460
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
99.80%
Dialogue to Total Word Ratio
(details)
97.8939%
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 spread the hand-drawn map across the hood of their dented minivan. It was covered in crayon, which she had stolen from a toddler at a restaurant earlier that morning. She tapped a wobbly circle near the center. "The presents will be stacked here, next to the bounce house," she said. "We'll have a forty-five second window between musical chairs and cake." Bill squinted at the map, turning it sideways. His balaclava was already on, though the party didn't start for three hours. "What about the clown?" he asked. "The clown is a non-issue. He's got a balloon animal queue until two-thirty. He'll be too busy making dachshunds to notice us." Bill chewed his lip. The afternoon sun beat down on the parking lot of the strip mall where they'd been conducting surveillance on the bounce house rental company for weeks. "And the parents?" "Distracted. I've arranged for a very aggressive essential oils salesperson to arrive at exactly two-fifteen." "That's diabolical," Bill whispered, genuine admiration softening his voice. "Thank you. Now put on your party hat. We're going in as grown adult guests, which means we need to look festive and completely unsuspicious." "Nobody will suspect a thing," Bill said, adjusting his balaclava beneath a glittery cone hat.
created_at
"2026-02-24T22:04:10.858Z"
2/24/2026, 10:04:10 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1780
moderation_latency
211
generation_time
12836
tokens_prompt
77
tokens_completion
405
native_tokens_prompt
92
native_tokens_completion
400
native_tokens_completion_images
(null)
native_tokens_reasoning
68
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
0.01046
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"8b0dafd7-b126-4284-9773-f16ca5db62a0"
is_byok
false
latency
1752
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771970650-oV5hWQJPkxFaQK4PGR8q"
upstream_id
"8b0dafd7-b126-4284-9773-f16ca5db62a0"
total_cost
0.01046
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
208
99.80%
Dialogue to Total Word Ratio
Ratio: 47.89%, Deviation: 2.11%
neededClean
false
wordsTotal
213
wordsDialogue
102
97.8939%