NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DA5JHR7QNYEQT87FNEHV2A
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.8s
Cost:
$0.001224
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
3.62%
Matches word count
(details)
17.73%
Dialogue to Total Word Ratio
(details)
10.6743%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 rain drummed on the roof of the getaway van as Molly pressed binoculars to her eyes. Across the street, the Hendersons' backyard glowed with balloons and a bouncy castle shaped like a dragon. Forty-three children shrieked at a pitch only dogs could hear, which suggested cake had been involved. Bill slid into the passenger seat, clutching a sack of tools and a suspiciously large bunny costume. "Presents on the porch," Molly whispered. "Only guard is a clown." Bill unfolded a napkin covered in arrows, one of which pointed directly at a cat. He nodded gravely, as though the cat were a serious obstacle. "Costume," Molly said. "Now." Bill sighed, zipped himself into the fluffy suit, and immediately sneezed three times. Feathers, or possibly ears, exploded across the seat. "Nobody suspects a rabbit of stealing a trampoline." Outside, the clown kept juggling the same three pins, looking more heartbroken with every drop of rain. Molly grabbed the sack, cracked her knuckles, and opened the door into the drizzle. "Perfect," she said. "Subtle as a fire alarm."
created_at
"2026-10-08T08:30:38.656Z"
10/8/2026, 8:30:38 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
10724
moderation_latency
(null)
generation_time
11769
tokens_prompt
75
tokens_completion
274
native_tokens_prompt
95
native_tokens_completion
2429
native_tokens_completion_images
(null)
native_tokens_reasoning
2021
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
0.001224
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448238-RZYeQ4lOqp6YO9vW5PG3"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448238-1AdD9QGvWLkiuKjXmoHF"
upstream_id
"msg_011CfpTV4UDBSMPEhKYvC9xB"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTV4UDBSMPEhKYvC9xB"
is_byok
false
latency
665
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.001224
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
3.62%
Matches word count
n/a
neededClean
false
words
176
17.73%
Dialogue to Total Word Ratio
Ratio: 21.47%, Deviation: 11.47%
neededClean
false
wordsTotal
177
wordsDialogue
38
10.6743%