NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DAGRPXHVBCN7HCW1SVQ40M
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.6s
Cost:
$0.000932
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
76.25%
Dialogue to Total Word Ratio
(details)
87.4790%
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, peering at the glowing windows of the Henderson house. Balloons bobbed on the porch, and somewhere inside a clown was screeching the birthday song off key. Beside her, Bill checked his fake moustache in a pocket mirror for the fourth time. "Right, listen carefully," Molly whispered, tapping a crumpled blueprint. "Phase one. You create a distraction at the back gate." "What kind of distraction?" Bill asked. "Something loud. Something that draws the parents outside." "Like what?" "You're the creative one. Pretend you're a lost puppy." "I'm not barking at anyone, Molly." "Then juggle something. Anything." Bill sighed and produced three bowling pins from inside his coat. "Fine. And what do you do?" "I slip through the kitchen, grab every present off the dining table, and out the window before anyone notices." "And if someone notices?" "Then I pretend I'm the magician's assistant." "You don't have a magician's assistant outfit." "I have a sequined leotard in my bag. Don't judge me." A shriek of laughter erupted from the house, followed by a sudden crash. Both thieves froze. "That," Bill said, "was either a cake or a very small bouncy castle."
created_at
"2026-10-08T08:36:45.416Z"
10/8/2026, 8:36:45 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
8932
moderation_latency
(null)
generation_time
8932
tokens_prompt
75
tokens_completion
309
native_tokens_prompt
95
native_tokens_completion
1844
native_tokens_completion_images
(null)
native_tokens_reasoning
1406
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
0.0009315
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448606-cZ8Vs2XmGqeD5ZO0qSn1"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448606-gicZzmjv0uOFASKRbZlb"
upstream_id
"msg_011CfpTx9JvcuSyKYfo5updH"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTx9JvcuSyKYfo5updH"
is_byok
false
latency
736
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0009315
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
76.25%
Dialogue to Total Word Ratio
Ratio: 57.22%, Deviation: 7.22%
neededClean
false
wordsTotal
194
wordsDialogue
111
87.4790%