NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DAKBAA1HEZQYNSQGGM58P2
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.2s
Cost:
$0.000930
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
3.62%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
1.8117%
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 getaway van smelled of damp cardboard and stale licorice. Molly crouched behind the steering wheel, binoculars pressed to her eyes, watching the house across the street, where a bouncy castle sagged beneath a banner reading HAPPY SIXTH, MAX! Beside her, Bill wriggled into an inflatable dinosaur costume he had borrowed from a different party. The tail squeaked every time he moved. "Why are we robbing a toddler?" "Gold foil means money," Molly said, not looking away from the lenses. "Those presents are wrapped like jewelry boxes." "Or they're tiny socks." "Phase one: distract the clown." She tapped the binoculars against the dashboard. "He's twisting balloon poodles for the parents. While they're distracted, we slip through the side gate." "And phase two?" "Phase two is the magician. He's about to make a rabbit disappear, and nobody notices a second disappearing act." Bill nodded solemnly, then tried to adjust his plastic dinosaur head. It fell off and rolled under the seat. "Remind me," he said, groping after it, "why I'm the dinosaur?" "Nobody suspects a dinosaur, Bill."
created_at
"2026-10-08T08:38:10Z"
10/8/2026, 8:38:10 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2651
moderation_latency
(null)
generation_time
12125
tokens_prompt
75
tokens_completion
585
native_tokens_prompt
95
native_tokens_completion
1841
native_tokens_completion_images
(null)
native_tokens_reasoning
1426
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
0.00093
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448690-sYcknWOUVIKvf0efCDzZ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448690-KWdIMLGXOIYEFCtoYl2y"
upstream_id
"msg_011CfpU4LXH3uNZuwfZf875C"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpU4LXH3uNZuwfZf875C"
is_byok
false
latency
826
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.00093
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
0.00%
Dialogue to Total Word Ratio
Ratio: 42.61%, Deviation: 32.61%
neededClean
false
wordsTotal
176
wordsDialogue
75
1.8117%