NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE8ZHZAHJJD7RZPTJKHY9PS
Run Details
Model:
Claude Sonnet 5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.2s
Cost:
$0.004926
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
12.81%
Dialogue to Total Word Ratio
(details)
16.4991%
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
The warehouse smelled of stale popcorn and desperation, which suited Molly and Bill just fine. Spread across the table between them was a hand-drawn map of the Hendricks estate, complete with little cartoon balloons marking the backyard where seventeen unopened birthday presents sat waiting like lambs to slaughter. Bill traced a finger along the fence line, muttering calculations under his breath. Molly leaned back in her chair, arms crossed, studying the bounce house sketched crudely in the corner of the map. "Bounce house is the weak point," she said. "Kids'll be distracted in there for twenty minutes, easy." Bill nodded slowly, still frowning at the details. He'd been in this business fifteen years and something about robbing seven-year-olds still nagged at him, though never enough to actually stop. "Clown's the real problem," he said finally. "Professional ones notice things." "So we become the entertainment." He looked up sharply. "You're not serious." "Dead serious. Face paint, red noses, the whole bit. Nobody questions a clown carrying a suspiciously heavy sack." Bill considered this, then allowed himself a small grin—the same grin he got before every job, equal parts thrill and dread. Molly was already sketching balloon animals shaped suspiciously like blueprints, humming some birthday tune under her breath, already three steps ahead as always. The presents never stood a chance.
created_at
"2026-07-01T07:23:32.726Z"
7/1/2026, 7:23:32 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3039
moderation_latency
(null)
generation_time
10875
tokens_prompt
77
tokens_completion
369
native_tokens_prompt
93
native_tokens_completion
474
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)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"end_turn"
service_tier
"default"
usage
0.004926
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_013A6YAytFrhU8nMbhNcTvpL"
is_byok
false
latency
3038
model_permaslug
"anthropic/claude-sonnet-5-20260630"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.17.0; linux; x64))"
http_referer
(null)
request_id
"req-1782890613-5x0Qz63urT5dSC3ZPchp"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890613-JUQfkgMC93rcCEGodvsN"
upstream_id
"msg_013A6YAytFrhU8nMbhNcTvpL"
total_cost
0.004926
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
20.19%
Matches word count
n/a
neededClean
false
words
220
12.81%
Dialogue to Total Word Ratio
Ratio: 21.97%, Deviation: 11.97%
neededClean
false
wordsTotal
223
wordsDialogue
49
16.4991%