NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8WKV2W14B7J26VTEKS1WW9
Run Details
Model:
Claude Sonnet 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 26s
Cost:
$0.147606
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
99.90%
Dialogue to Total Word Ratio
(details)
98.7640%
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 floor plan across the hood of their rusty van and tapped it with her finger. The van smelled of old cheese and regret, which was honestly appropriate. "The bouncy castle is our biggest problem," she said. Bill squinted at the diagram. "We go under it." "Under the bouncy castle." "Like a tunnel." "Bill, it's inflatable." He stared at her. "We go over it then." "We are not going over a bouncy castle." "Then what's the plan, Molly?" "We walk around it. The presents are stacked by the garden wall. We grab the bags, we're gone in forty seconds." Bill nodded slowly. Outside, the muffled screech of twenty-three sugar-crazed six-year-olds drifted through the afternoon air. Pink balloons bobbed over the fence of number fourteen like cheerful little warnings. "What if the clown sees us?" "Avoid the clown." "I can't avoid the clown. He finds me, Molly. He always finds me." "Then we deal with the clown." "How do you deal with a clown?" She rolled up the floor plan with a sigh. Every job had one unexpected complication. Usually it involved lasers or tripwires. Today it was a man named Blinky.
created_at
"2026-02-24T22:34:15.524Z"
2/24/2026, 10:34:15 PM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
707
moderation_latency
144
generation_time
86150
tokens_prompt
77
tokens_completion
1124
native_tokens_prompt
92
native_tokens_completion
9822
native_tokens_completion_images
(null)
native_tokens_reasoning
817
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
0.147606
router
(null)
provider_responses
0
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
id
"88a32437-e474-4f09-afc3-38f8791e680a"
is_byok
false
latency
707
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771972455-zHDLwWef09sMpoR7hzQa"
upstream_id
"88a32437-e474-4f09-afc3-38f8791e680a"
total_cost
0.147606
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
193
99.90%
Dialogue to Total Word Ratio
Ratio: 48.22%, Deviation: 1.78%
neededClean
false
wordsTotal
197
wordsDialogue
95
98.7640%