NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DYSN5Y42J4RMH8HXK9CEF8
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.6s
Cost:
$0.000620
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
82.08%
Dialogue to Total Word Ratio
(details)
86.2796%
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 community center, headlights off, engine sputtering like a nervous hamster. Molly unfolded a blueprint across the dashboard and tapped a sketch of a bouncy castle. "Kitchen window," she said. Bill squinted at the paper, then at a crayon drawing taped beside it. "Is that a clown?" he asked, pointing. "Ignore it," Molly said. She pulled a black ski mask over her curls and tossed him a matching one, pink with a unicorn horn. "Absolutely not." Bill held it up like a dead fish. "I'm not robbing a birthday party dressed as a unicorn." "Nobody looks at the masked guy." Through the brick wall came a ragged chorus of "Happy Birthday," wobbling badly off key. Bill sighed, pulled on the unicorn hat, and checked his watch. The presents were stacked in the living room, wrapped in glittery paper, each one tagged with a child's name in careful, lopsided letters. "Ten minutes," he whispered. Somewhere inside, a seven-year-old shrieked with joy, and both thieves froze, guilt flickering across their faces like a candle in a draft. Molly swallowed hard and reached for the door handle. "Right. Go."
created_at
"2026-10-08T14:31:08.231Z"
10/8/2026, 2:31:08 PM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2790
moderation_latency
(null)
generation_time
7611
tokens_prompt
75
tokens_completion
432
native_tokens_prompt
95
native_tokens_completion
1220
native_tokens_completion_images
(null)
native_tokens_reasoning
795
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
0.0006195
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791469868-tHggJc6BjoEdlgah3q32"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791469868-q9KdzRTnNRpQ6kaoSlZ0"
upstream_id
"msg_011CfpvyUeS6ML7ZDz3LS7hm"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpvyUeS6ML7ZDz3LS7hm"
is_byok
false
latency
897
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0006195
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
90.48%
Matches word count
n/a
neededClean
false
words
190
82.08%
Dialogue to Total Word Ratio
Ratio: 16.67%, Deviation: 6.67%
neededClean
false
wordsTotal
192
wordsDialogue
32
86.2796%