NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-09-01M4G14MW0K2FVGJ34WFVN9NFC
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.1s
Cost:
$0.001161
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
90.85%
Dialogue to Total Word Ratio
(details)
90.6659%
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 warehouse, headlights off, windows fogged with nervous breath. Molly tapped a laminated map of the Henderson twins' birthday party against the steering wheel. Bill sat beside her in a clown wig he had bought for the occasion and was clearly enjoying it far too much. "In through the kitchen," Molly whispered. "Out through the balloon arch." Bill nodded solemnly, adjusting his fake mustache. "And if the magician spots us?" "Pretend to be the magician." Outside, shrieks of delighted children rattled the windows. A gorilla-suited uncle stumbled past carrying a tray of cupcakes, and both thieves ducked below the dashboard. Bill's wig slid over one eye, and he blew it back into place with a huff. Through the fogged glass, they could see the mountain of glitter-wrapped presents stacked beside the birthday cake, each box tied with ribbons large enough to hide a getaway car. Bill glanced down at the bag he had packed, which contained nothing but plastic handcuffs and kazoos. He sighed, wiped his nose on his sleeve, and pulled on a ski mask shaped like a pony. Molly checked her watch, cracked her knuckles, and reached for the door handle. "Let's go steal some birthday loot," she said with a grin.
created_at
"2026-10-09T09:50:34.374Z"
10/9/2026, 9:50:34 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3478
moderation_latency
(null)
generation_time
12020
tokens_prompt
75
tokens_completion
588
native_tokens_prompt
95
native_tokens_completion
2303
native_tokens_completion_images
(null)
native_tokens_reasoning
1849
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
0.001161
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791539434-7u2lwBtE9P9YwKvD6YkM"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791539434-LBpEStoSVcKjkWQv6Z1H"
upstream_id
"msg_011CfrTPVN1f619uu3koCSR9"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfrTPVN1f619uu3koCSR9"
is_byok
false
latency
814
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.001161
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
210
90.85%
Dialogue to Total Word Ratio
Ratio: 15.57%, Deviation: 5.57%
neededClean
false
wordsTotal
212
wordsDialogue
33
90.6659%