NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8X06QE2HXH5WVH95R0Q7FZ
Run Details
Model:
Claude Sonnet 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 53s
Cost:
$0.191811
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 unrolled the hand-drawn blueprint across the park bench, her coffee-stained fingers tracing the perimeter of what was, by any reasonable assessment, the most heavily fortified sixth birthday party in suburban history. Seven bouncy castles. Three face painters. One alarmingly alert grandmother stationed near the gift table like a retired intelligence operative with excellent peripheral vision. Bill pulled his too-small baseball cap lower and studied the diagram with the expression of a man facing his greatest professional challenge. "The clown is the variable," he said gravely. "I have never once trusted a clown in my career." Molly nodded. She had anticipated the clown. She had not, however, anticipated the eleven children currently practicing karate kicks in the driveway, which she circled on the blueprint with a small alarmed mark. The target was a towering pile of presents near the back fence, wrapped in aggressively bright paper and topped with enormous curling bows. Conservative estimates placed the haul at around forty gifts. "We move at cake time," Molly said. The logic was airtight. Sugar-deranged children would generate perfect chaos. Bill straightened his sliding fake mustache and attempted to look like a professional criminal rather than a hopeful amateur on a bench.
created_at
"2026-02-24T22:41:00.663Z"
2/24/2026, 10:41:00 PM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
634
moderation_latency
142
generation_time
113136
tokens_prompt
77
tokens_completion
1298
native_tokens_prompt
92
native_tokens_completion
12769
native_tokens_completion_images
(null)
native_tokens_reasoning
965
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
0.191811
router
(null)
provider_responses
0
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
id
"c9f45952-14ce-44ee-9219-fd168aac0d7b"
is_byok
false
latency
627
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771972860-bVyNDQ9h7Vq2JUUI9mXL"
upstream_id
"c9f45952-14ce-44ee-9219-fd168aac0d7b"
total_cost
0.191811
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
100.00%
Dialogue to Total Word Ratio
Ratio: 9.80%, Deviation: 0.20%
neededClean
false
wordsTotal
204
wordsDialogue
20
100.0000%