NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE8WY48SHQJN76H2P73N33A
Run Details
Model:
Claude Sonnet 5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.7s
Cost:
$0.004926
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
51.23%
Dialogue to Total Word Ratio
(details)
75.4897%
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
"Okay, so it's a six-year-old's birthday party," Molly said. "How hard can it be?" "Six-year-olds travel in packs, Molly. Packs of screaming, sugar-crazed little monsters." "They're children, Bill, not wolves." "Same thing. Same teeth, even, once they lose the baby ones." "Focus. The presents are on the table by the bounce house. We go in disguised as the entertainment—" "Absolutely not. I am not putting on that clown costume again." "It's not a clown costume, it's a 'whimsical party jester' costume." "It has a bell on the hat, Molly." "One bell!" "I have standards." "You robbed a church bake sale last Tuesday." "That was different. Those cupcakes had my name on them, spiritually." "Fine. New plan. You're the pizza delivery guy. I'll be the magician's assistant. Nobody questions a magician's assistant." "Nobody questions a magician's assistant because nobody notices a magician's assistant. That's the whole point of the job." "Exactly! So while the real magician is pulling scarves out of his sleeve, I'm pulling presents into a duffel bag." "And if some kid asks where the presents went?" "I tell him the rabbit ate them." "...That's actually not bad." "I know. Now go get the pizzas. And Bill—no eating the evidence this time."
created_at
"2026-07-01T07:22:06.869Z"
7/1/2026, 7:22:06 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1968
moderation_latency
(null)
generation_time
8690
tokens_prompt
77
tokens_completion
344
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_01KRAjcTxtcEjFru9facvu9f"
is_byok
false
latency
1959
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-1782890526-8Hk2m2ZRWfbKPdf8Aw41"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890526-LvZEcT2jpnHTSidFoutM"
upstream_id
"msg_01KRAjcTxtcEjFru9facvu9f"
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
99.74%
Matches word count
n/a
neededClean
false
words
204
51.23%
Dialogue to Total Word Ratio
Ratio: 99.04%, Deviation: 9.04%
neededClean
false
wordsTotal
209
wordsDialogue
207
75.4897%