NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DAH038Y26G8ZQBBVZEYHQT
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
14.0s
Cost:
$0.001506
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
99.3534%
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 rented van idled behind a bouncy castle warehouse, headlights off, windows fogged with nervous breath. Molly tapped a laminated floor plan against the steering wheel while Bill squinted across the street at the Henderson house, where forty-two balloons bobbed along the porch like a plague of rainbows. Inside, a dozen children screamed the words to a song about a purple dinosaur. "Mountains of presents, one unlocked back door, and a clown who drinks." Molly grinned. Bill nodded gravely and unfolded the pillowcase he had brought as a sack. It was printed with cartoon ducks, which he considered an excellent disguise. He adjusted a fake mustache that slid downward the moment he exhaled. Molly handed him a cone-shaped party hat, slightly crushed, reading HAPPY BIRTHDAY in gold foil. He put it on with dignity. Across the street, the front door burst open. A sugar-crazed toddler sprinted onto the lawn waving a plastic sword, chased by a sobbing parent who was clearly losing. Bill watched the chaos with professional admiration. Somewhere, a balloon popped, and nobody flinched. Their plan had survived worse, though rarely this many toddlers. "Right," Bill said. "Let's go steal some Lego."
created_at
"2026-10-08T08:36:52.978Z"
10/8/2026, 8:36:52 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
13955
moderation_latency
(null)
generation_time
13956
tokens_prompt
75
tokens_completion
304
native_tokens_prompt
95
native_tokens_completion
2993
native_tokens_completion_images
(null)
native_tokens_reasoning
2553
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
0.001506
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448612-AsaYaKvw6WHFOpk5jnik"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448612-b7Rm7UXS7Pf0QRQOzfog"
upstream_id
"msg_011CfpTxf17RsCA9WsoPxMPx"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTxf17RsCA9WsoPxMPx"
is_byok
false
latency
905
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.001506
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
99.99%
Dialogue to Total Word Ratio
Ratio: 9.14%, Deviation: 0.86%
neededClean
false
wordsTotal
197
wordsDialogue
18
99.3534%