NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ932M4VRAF4X28YY544ZKE
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.3s
Cost:
$0.005025
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
99.78%
Dialogue to Total Word Ratio
(details)
93.0796%
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
"Right, so the birthday is at two o'clock," Molly said, spreading the hand-drawn map across the hood of the van. "Who drew this? A toddler?" Bill squinted at the crayon markings. "Focus. The presents will be in the living room, near the inflatable dinosaur." "There's an inflatable dinosaur?" "Bill." "Sorry, sorry. What about the parents?" "Occupied. Twelve screaming seven-year-olds playing pass the parcel will do that to a person." "And the cake situation?" "What about the cake situation?" "I'm just saying, if we're already in there..." "We are not stealing a child's birthday cake, Bill." "Just a slice." "Absolutely not." "Half a slice." "I will leave you here." Bill folded his arms. "How do we get out with all the presents without anyone noticing?" "We wear the clown costumes." "I knew there were clown costumes. I knew it from the moment you called me at six this morning with that tone." "What tone?" "Your clown tone." "I don't have a clown tone." "Molly, you absolutely have a clown tone." "Just put the wig on." "Does it have to be the red one?" "Get in the van."
created_at
"2026-02-18T02:26:05.473367+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
706
moderation_latency
170
generation_time
7036
tokens_prompt
77
tokens_completion
312
native_tokens_prompt
75
native_tokens_completion
320
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
0.005025
router
(null)
provider_responses
0
id
"7f830f92-446a-49a4-bc0e-aca1afc39251"
status
200
is_byok
false
latency
706
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381557-62Sok8Tm1uLTfdeMvpho"
upstream_id
"7f830f92-446a-49a4-bc0e-aca1afc39251"
total_cost
0.005025
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
189
99.78%
Dialogue to Total Word Ratio
Ratio: 87.83%, Deviation: 2.17%
neededClean
false
wordsTotal
189
wordsDialogue
166
93.0796%