NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ932B3Y2E3G89NTNF98WG9
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.2s
Cost:
$0.004575
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
60.01%
Dialogue to Total Word Ratio
(details)
79.3599%
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 crouched behind the garden hedge, her black turtleneck already itching in the afternoon heat. She peered through the leaves at the birthday party unfolding in the backyard, watching six-year-olds hurl cake at one another with gleeful abandon. The pile of wrapped presents on the gift table was enormous, a glittering mountain of ribbons and shiny paper that practically sang to her professional instincts. Bill crawled up beside her, snapping three twigs loudly in the process. He was wearing sunglasses despite the cloud cover and had inexplicably brought a briefcase. "The presents," Molly whispered. Bill nodded gravely. "Tonight." She studied the layout with practiced eyes. The bouncy castle provided cover on the eastern flank. A distracted clown was fumbling balloon animals near the fence. Parents clustered around the drinks table, increasingly desperate looking. The birthday child, one Magnus Pembrook-Hayes, sat in his throne-like chair wearing a paper crown, surveying his kingdom with the casual cruelty only a six-year-old can project. Molly pulled out her notepad and sketched the scene. This would require timing, precision, and an exit strategy that accounted for at least one inevitable tantrum, probably from Bill.
created_at
"2026-02-18T02:26:05.286546+00:00"
2/18/2026, 2:26:05 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
538
moderation_latency
90
generation_time
7007
tokens_prompt
77
tokens_completion
319
native_tokens_prompt
75
native_tokens_completion
290
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
0.004575
router
(null)
provider_responses
0
id
"42507346-0124-4902-96e6-6f9166183008"
status
200
is_byok
false
latency
538
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381557-ld3rM7g9fPnUWG7nFuCc"
upstream_id
"42507346-0124-4902-96e6-6f9166183008"
total_cost
0.004575
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
194
60.01%
Dialogue to Total Word Ratio
Ratio: 1.55%, Deviation: 8.45%
neededClean
false
wordsTotal
194
wordsDialogue
3
79.3599%