NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEA9W7Y3NEMNMQ6SKVH81F6
Run Details
Model:
Claude Sonnet 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.8s
Cost:
$0.004706
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
84.14%
Dialogue to Total Word Ratio
(details)
90.8823%
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
"So let me get this straight," Molly said, arms crossed. "We're robbing an eight-year-old's birthday party." "Not just any eight-year-old," Bill said, grinning. "Timmy Beaumont. His dad owns half the shipping yards downtown. That kid's presents are worth more than our last three jobs combined." "Bill, there's gonna be, like, twenty kids there. And clowns. I hate clowns." "No clowns. I checked. It's a magician. Name's 'The Great Fernando.'" "Oh, well, that's completely different then. A magician makes everything better." "Molly, focus. We go in as caterers, grab the gift table during cake time, out the back before anyone notices." "And what exactly is our cover story if someone asks why two caterers are stuffing Lego sets into a duffel bag?" "We tell them it's a magic trick. Fernando's assistants." "That's your plan? 'We're with the magician'?" "You got a better one?" "Yeah, we skip the party and rob a bank like normal criminals." "Banks have guards, Molly. This has a bouncy castle." "That somehow makes it worse." "Fine, don't come. More presents for me." "There's a Nintendo Switch on that table, isn't there." "Two of them, actually." "...I'll get the duffel bags."
created_at
"2026-07-01T07:46:39.497Z"
7/1/2026, 7:46:39 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1746
moderation_latency
(null)
generation_time
8754
tokens_prompt
77
tokens_completion
324
native_tokens_prompt
93
native_tokens_completion
452
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
0.004706
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01L3dXiuBhea474FcsrRsxMe"
is_byok
false
latency
1746
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-1782891999-QxYnPmqHAxdeVOKqJEHo"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891999-D41cFaf2VIcM8A9LKz6R"
upstream_id
"msg_01L3dXiuBhea474FcsrRsxMe"
total_cost
0.004706
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
97.63%
Matches word count
n/a
neededClean
false
words
193
84.14%
Dialogue to Total Word Ratio
Ratio: 96.45%, Deviation: 6.45%
neededClean
false
wordsTotal
197
wordsDialogue
190
90.8823%