NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4D9YDD94GVQ1N0H4JMCBZAZ
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.8s
Cost:
$0.001045
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
39.93%
Dialogue to Total Word Ratio
(details)
57.5438%
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, eyes fixed on the glowing windows of number twelve. Balloons bobbed against the glass. Beside her, Bill adjusted his fake moustache and consulted a crumpled clipboard. "Right," he whispered. "Phase one. We slip through the back door while the clown performs his magic show." "Bill, that clown is a professional. He'll spot us." "He's busy. Balloon animals require tremendous concentration." "Fine. And phase two?" "We grab every present wrapped in shiny paper. Avoid anything with a lopsided bow. Those are homemade, and mothers always notice when something goes missing." Molly squinted at the clipboard. "Why does the list say 'Dinosaur Kit, Dave's Birthday, Do Not Touch'?" "Because I'm organised, and Dave's birthday is Thursday." "Wait, you're robbing a six-year-old?" "I'm robbing the adults, Molly. Children only get the wrapping paper. Now stop asking questions and follow me, or I'm eating the chocolate coins myself." Somewhere inside, a child shrieked with delight, and a tuba began to wheeze. Molly sighed, tightened her gloves, and crept toward the back door. Bill followed, tripping over a garden gnome that appeared to be laughing at him.
created_at
"2026-10-08T08:26:44.017Z"
10/8/2026, 8:26:44 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
9739
moderation_latency
(null)
generation_time
9739
tokens_prompt
75
tokens_completion
304
native_tokens_prompt
95
native_tokens_completion
2071
native_tokens_completion_images
(null)
native_tokens_reasoning
1614
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
0.001045
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448004-rJaOK2eok3fZj9CUaeJV"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448004-kBK1RoaLt3LBUjJRsf6q"
upstream_id
"msg_011CfpTBmPafPwSzk3AD6xDK"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTBmPafPwSzk3AD6xDK"
is_byok
false
latency
748
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.001045
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
75.16%
Matches word count
n/a
neededClean
false
words
187
39.93%
Dialogue to Total Word Ratio
Ratio: 59.79%, Deviation: 9.79%
neededClean
false
wordsTotal
189
wordsDialogue
113
57.5438%