NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8W70NJ99ACQ3B353QMJD79
Run Details
Model:
Claude Sonnet 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 33s
Cost:
$0.157836
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 spread the crayon-drawn map across the hood of their battered van, smoothing out the corners with the kind of reverence usually reserved for ancient treasure charts. The map, borrowed from a seven-year-old cousin without his knowledge, featured a house surrounded by what appeared to be either guard dogs or aggressive balloons. Bill squinted at it, chewing the end of a plastic straw. The target was a birthday party for one Timothy Henderson, age six, whose parents had apparently invited every child within a five-mile radius and received enough wrapped presents to stock a toy store. Molly had conducted her reconnaissance sitting in a parked car, wearing oversized sunglasses and eating a bag of pretzels with tremendous professionalism. "The bouncy castle is our blind spot," Molly said, tapping the map. "Brilliant. I'll wear the full clown suit. Nobody ever questions a clown anyway," said Bill. The plan was elegant in its absurdity. They would arrive during the cake ceremony, when every adult eye would be fixed on Timothy annihilating a fondant dinosaur. The presents, piled in an unsupervised hallway, would be loaded into the van in four minutes. Molly had timed it using a stopwatch shaped like a rubber duck.
created_at
"2026-02-24T22:27:15.258Z"
2/24/2026, 10:27:15 PM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
717
moderation_latency
157
generation_time
93193
tokens_prompt
77
tokens_completion
1172
native_tokens_prompt
92
native_tokens_completion
10504
native_tokens_completion_images
(null)
native_tokens_reasoning
857
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
0.157836
router
(null)
provider_responses
0
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
id
"e0d19d41-bd85-438b-9f1c-dc7130c39c52"
is_byok
false
latency
716
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771972035-AB1uGvg0rvErLEtiYBzH"
upstream_id
"e0d19d41-bd85-438b-9f1c-dc7130c39c52"
total_cost
0.157836
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%