NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEA0S28V2VHECQP78XP2YYZ
Run Details
Model:
Claude Sonnet 5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.9s
Cost:
$0.004736
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
99.91%
Dialogue to Total Word Ratio
(details)
84.0050%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
Bill leaned against the van, arms crossed. "So let me get this straight. We're robbing a six-year-old's birthday party." "Not just any birthday party, Bill. Timmy Fenwick's birthday party. His dad's the guy who owes Sal forty grand." "So we're stealing a kid's presents to settle his old man's debt." "When you say it like that it sounds bad." "It IS bad, Molly." "It's poetic justice." "It's felony theft from a child." "Look, are you in or not? The bounce house is at three, present-opening's at four-thirty, and by five those gifts are getting split up among forty screaming children who won't even remember what they got." Bill sighed. "Fine. What's the plan?" "You dress as the clown." "Absolutely not." "You're the only one who fits the costume, Bill." "I fit the costume because I'm five foot six, not because I asked for this." "The clown does balloon animals near the gift table. I come in as catering, we grab the loot during the piƱata chaos, out the back before cake." "And if some kid notices?" "They're six, Bill. Tell them the presents went to Narnia." "That's your actual plan?" "You got a better one?" Bill groaned, grabbing the rainbow wig off the dashboard. "I hate you." "Love you too. Now go be funny."
created_at
"2026-07-01T07:41:41.334Z"
7/1/2026, 7:41:41 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3507
moderation_latency
(null)
generation_time
10901
tokens_prompt
77
tokens_completion
340
native_tokens_prompt
93
native_tokens_completion
455
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
0.004736
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01Jq6sUjfhkVr5ooz8ogTHey"
is_byok
false
latency
3507
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-1782891701-mgloP1gUpBpG8dAJuUoC"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891701-5d53rsfzLOAzYx55QqaE"
upstream_id
"msg_01Jq6sUjfhkVr5ooz8ogTHey"
total_cost
0.004736
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
68.10%
Matches word count
n/a
neededClean
false
words
214
99.91%
Dialogue to Total Word Ratio
Ratio: 91.74%, Deviation: 1.74%
neededClean
false
wordsTotal
218
wordsDialogue
200
84.0050%