NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DA6M7YMF6MZ1X6V0R9D14Y
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.0s
Cost:
$0.001045
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
94.52%
Dialogue to Total Word Ratio
(details)
96.6174%
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 a bouncy castle warehouse, headlights off and engine ticking like a nervous clock. Molly spread a blueprint across the hood, a crayon-scribbled map of Tommy Pickett's seventh birthday party. Bill squinted through binoculars shaped like a dinosaur. "Vents?" Bill asked. "Vents," Molly said. "Forty feet of ductwork, right above the cake table." Bill nodded gravely and adjusted his ski mask, which bore a cartoon unicorn. He had insisted on it. Nobody suspects a unicorn, he had argued, and Molly had lost the argument by lunchtime. Through the warehouse windows, forty children shrieked in unison while a clown with a squeaky voice led a conga line past the gift table. Mountains of glittering boxes towered beside a plastic princess castle. "Every one of them is going in our bag," Molly said. "Even the ones shaped like socks." Bill pulled a rope from his jacket and tied it to the roof rack with a knot he'd learned from a sailing video. It came loose immediately. He tied it again, muttering under his breath. "Ready?" Molly asked. "Born ready," Bill said, then tripped over a tricycle and scattered the blueprints across the pavement.
created_at
"2026-10-08T08:31:13.174Z"
10/8/2026, 8:31:13 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
10966
moderation_latency
(null)
generation_time
10966
tokens_prompt
75
tokens_completion
296
native_tokens_prompt
95
native_tokens_completion
2071
native_tokens_completion_images
(null)
native_tokens_reasoning
1635
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
0.001045
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448273-BiGtHKx9rnLbMonwDo4d"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448273-xdEFgSGIi5Qp90ktTR9a"
upstream_id
"msg_011CfpTXcbYrWhzqP5ZwhoXq"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTXcbYrWhzqP5ZwhoXq"
is_byok
false
latency
751
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.001045
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
98.71%
Matches word count
n/a
neededClean
false
words
194
94.52%
Dialogue to Total Word Ratio
Ratio: 14.87%, Deviation: 4.87%
neededClean
false
wordsTotal
195
wordsDialogue
29
96.6174%