NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4D9ZVAV36WYVB1XPH96Q30W
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.5s
Cost:
$0.000808
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
99.70%
Dialogue to Total Word Ratio
(details)
83.9023%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Molly crouched behind the hedge, binoculars pressed to her eyes, watching the glowing windows of number fourteen Maple Lane. Bouncy castles sagged in the garden, and a cluster of helium balloons bobbed against the gate like nervous ghosts. Beside her, Bill rustled a sack that clinked suspiciously. "Balloons on the gate, bouncy castle in the yard," she whispered. "Bill, this is a fortress made of sugar." Bill adjusted his fake moustache and checked his pocket watch. "Simple plan. We slip through the cat flap, grab every present from the hall table, and vanish before the magic show ends." "The magician has been staring at us for ten minutes." "He's a magician, Molly. They always stare. It's the job." The sack let out a loud squeak. "Quiet, you." Molly lowered the binoculars and glared at him. "What's in the sack?" "Sausages for the dog. Plus a backup plan." "And the backup plan?" "If anyone wakes up, we declare ourselves the entertainment and start juggling." She stared at him for a long moment. Inside the house, a hundred children shrieked with joy, and sparklers hissed like angry bees. Molly sighed, checked her own watch, and started crawling toward the back door. "Cake's in five minutes," she muttered. "Let's go be the most suspicious guests in history."
created_at
"2026-10-08T08:27:31.043Z"
10/8/2026, 8:27:31 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
8449
moderation_latency
(null)
generation_time
8449
tokens_prompt
75
tokens_completion
327
native_tokens_prompt
95
native_tokens_completion
1597
native_tokens_completion_images
(null)
native_tokens_reasoning
1124
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
0.000808
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448051-FftR4mYwwrEFT2YBdoj0"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448051-FuUMhqqnUpfwCjCY5A1l"
upstream_id
"msg_011CfpTFEPsTTEPg8ence2ga"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTFEPsTTEPg8ence2ga"
is_byok
false
latency
730
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.000808
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
68.10%
Matches word count
n/a
neededClean
false
words
214
99.70%
Dialogue to Total Word Ratio
Ratio: 47.66%, Deviation: 2.34%
neededClean
false
wordsTotal
214
wordsDialogue
102
83.9023%