NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4E09Y1W1Z72HFREC1QX80FM
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 13s
Cost:
$0.009732
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9997%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Molly spread the blueprints across the hood of their stolen ice cream van, pinning the corners with a squashed cupcake and a stapler. "Phase one: we slip through the back gate while the magician is busy with his balloon swords." Bill snapped on a rubber clown nose and gave it a nervous honk. "Why am I always the clown?" "Because nobody ever checks a clown's pockets." She tapped the paper. "The presents are stacked on the patio, wrapped in glitter paper with enormous bows. We grab everything and drive." Bill squinted at the bouncy castle, where toddlers shrieked like seagulls over a dropped chip. "What about the kids?" "Easy. We bribe them with a piñata. Nobody has ever resisted a piñata." "Last time I tried that, a six-year-old swindled me out of my wristwatch for one lollipop." Molly sighed deeply, folded the map into a tiny, tragic square, and stuffed it into her boot. "Look, Bill, this is the cleanest heist of the year. Nobody gets hurt, and nobody will even notice." A balloon popped somewhere behind the hedge with a sound like a gunshot. Both thieves dove headfirst behind the van, shrieking louder than any toddler at the party.
created_at
"2026-10-08T14:57:30.184Z"
10/8/2026, 2:57:30 PM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2783
moderation_latency
(null)
generation_time
73338
tokens_prompt
75
tokens_completion
2557
native_tokens_prompt
95
native_tokens_completion
19446
native_tokens_completion_images
(null)
native_tokens_reasoning
19016
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
0.0097325
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791471450-wpvAikkPr2rasc6JU6Wp"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791471450-6oNueps10yrVjcMn2Gvw"
upstream_id
"msg_011Cfpxz8GrHA7twQKppF96U"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011Cfpxz8GrHA7twQKppF96U"
is_byok
false
latency
1279
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0097325
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Claude Platform on AWS"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 50.50%, Deviation: 0.50%
neededClean
false
wordsTotal
202
wordsDialogue
102
99.9997%