NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DAJH243C3V3FC5DCX1V5A9
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.8s
Cost:
$0.000972
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
14.30%
Matches word count
(details)
99.87%
Dialogue to Total Word Ratio
(details)
57.0867%
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 van idled behind the bouncy castle hire shop, headlights off, engine coughing like a retired pensioner. Molly tugged a balaclava over her curls and studied a blueprint she had sketched on the back of a pizza box. Bill leaned against the side door, licking frosting off his thumb. "Is that the cake?" Molly asked. "Reconnaissance," Bill said solemnly. "Quality control." Across the street, number twelve blazed with light. Balloons bobbed against the bay window, and somewhere a clown was shouting about musical chairs. Their target was a sprawling living room, a crackling fireplace, and forty-two presents wrapped in paper covered with cartoon dinosaurs. Security consisted of one dad named Gary, who had fallen asleep during the piƱata and was now snoring into a bowl of crisps. Molly checked her watch. "Ten minutes until the sugar crash. Still snoring?" "Like a chainsaw," Bill whispered. Bill grinned and pulled a rubber chicken and a can of silly string from his jacket. He squeezed the chicken, which squawked loudly enough to rattle the gutters. Molly groaned, clamped a hand over his mouth, and dragged him toward the garden gate. Behind the hedge, a small figure in a dinosaur onesie pressed its face to the glass and held up a handmade sign: PLEASE TAKE THE PONY. Molly sighed. Some heists were simply too easy.
created_at
"2026-10-08T08:37:43.114Z"
10/8/2026, 8:37:43 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
9732
moderation_latency
(null)
generation_time
9732
tokens_prompt
75
tokens_completion
338
native_tokens_prompt
95
native_tokens_completion
1925
native_tokens_completion_images
(null)
native_tokens_reasoning
1428
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
0.000972
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448663-AsJK2UYdvxJsZc498WfC"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448663-j4kqDZjqOgGGZaOTuMXE"
upstream_id
"msg_011CfpU2MJrBpm9DMBhqFtJm"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpU2MJrBpm9DMBhqFtJm"
is_byok
false
latency
796
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.000972
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
14.30%
Matches word count
n/a
neededClean
false
words
221
99.87%
Dialogue to Total Word Ratio
Ratio: 8.11%, Deviation: 1.89%
neededClean
false
wordsTotal
222
wordsDialogue
18
57.0867%