NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-08-01KGYXQETV9KCEERGXVRKE4VHB
Run Details
Model:
Claude Haiku 4.5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.5s
Cost:
$0.001520
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
0.21%
Matches word count
(details)
99.82%
Dialogue to Total Word Ratio
(details)
50.0155%
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
# The Birthday Caper "So we hit the Henderson place Saturday at 2 PM sharp," Molly said, checking her clipboard. "During the piƱata chaos?" Bill asked hopefully. "Exactly. Maximum confusion, minimum witnesses." "What about the dog? The golden retriever?" "Easy. I've got three pounds of premium bacon. That mutt will follow us anywhere." Bill whistled low. "What's the target haul?" "According to my intel, at least forty wrapped presents. Video game consoles, remote control cars, the works." "What about security? Do six-year-olds have motion sensors now?" "Just sticky fingers and loose lips. We'll be in and out in eight minutes." "Eight? That's optimistic." "You got a better plan, Bill?" "Maybe we don't steal from children's birthday parties?" Molly stared at him. "Did you hit your head?" "Just asking." "We've robbed banks, museums, and that casino in Atlantic City. But you draw the line at birthday presents?" Bill sighed. "No, you're right. It's stupid to have standards now." "That's what I thought. Now grab the duffel bags and let's go buy that bacon."
created_at
"2026-02-08T15:25:41.714131+00:00"
2/8/2026, 3:25:41 PM
model
"anthropic/claude-4.5-haiku-20251001"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1293
moderation_latency
131
generation_time
4256
tokens_prompt
61
tokens_completion
251
native_tokens_prompt
75
native_tokens_completion
289
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
0.00152
router
(null)
provider_responses
0
id
"a72bef88-e3f2-42bd-a146-dbb0061af435"
status
200
is_byok
false
latency
1292
endpoint_id
"d000261c-5aeb-47d1-ac87-ad64dbe1cdb6"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.5-haiku-20251001"
api_type
"completions"
id
"gen-1770564336-qPznFddioXkG5eyOkHfF"
upstream_id
"a72bef88-e3f2-42bd-a146-dbb0061af435"
total_cost
0.00152
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
0.21%
Matches word count
n/a
neededClean
false
words
172
99.82%
Dialogue to Total Word Ratio
Ratio: 87.93%, Deviation: 2.07%
neededClean
false
wordsTotal
174
wordsDialogue
153
50.0155%