NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ94BEZRPA5BCVB8VG6QTNB
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
6.5s
Cost:
$0.004785
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
80.1376%
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 back against the brick wall and peered around the corner at the bouncy castle. A banner reading "Happy 7th Birthday Tyler!" flapped in the breeze like a taunt. "The presents are stacked near the picnic table," she whispered, adjusting her balaclava. Bill squinted through tiny binoculars shaped like a duck. "I count at least thirty packages. Maybe forty." "We go in during the cake song," Molly said. "Everyone looks at the cake during the cake song." "What if they have a clown?" Bill asked, his voice cracking slightly. "Why would a clown be a problem?" "Clowns are unpredictable, Molly. Everyone knows that." She grabbed his collar. "You robbed the National Museum of Art twice." "That museum didn't have a clown." Molly released him and exhaled slowly. A chorus of tiny screaming children erupted from the garden as someone unleashed a piƱata. Both thieves flinched. "Maybe we should rob a bank instead," Bill offered. "Banks have security cameras." "And this has forty-seven children armed with party poppers." Molly checked her watch. The cake song was starting. She cracked her knuckles. "Let's move."
created_at
"2026-02-18T02:26:46.627091+00:00"
2/18/2026, 2:26:46 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
621
moderation_latency
187
generation_time
6256
tokens_prompt
77
tokens_completion
307
native_tokens_prompt
75
native_tokens_completion
304
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.004785
router
(null)
provider_responses
0
id
"bdec7079-384b-46de-a6d6-8eebd08ed175"
status
200
is_byok
false
latency
621
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381599-Rgi0Jp4jYJAappZ5Tdvq"
upstream_id
"bdec7079-384b-46de-a6d6-8eebd08ed175"
total_cost
0.004785
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
185
100.00%
Dialogue to Total Word Ratio
Ratio: 50.27%, Deviation: 0.27%
neededClean
false
wordsTotal
185
wordsDialogue
93
80.1376%