NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DAFTA0TF09N35GGE15CFPS
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.9s
Cost:
$0.001315
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
90.6300%
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 getaway van idled behind a hedge of frostbitten holly, headlights off, engine purring like a nervous cat. Molly drummed her gloved fingers on the steering wheel while Bill squinted at a map drawn in crayon, presumably by the party's six-year-old. Across the street, forty balloons bobbed above a sparkling mansion, and a clown on stilts juggled flaming torches with frightening confidence. Inside the house, somewhere past the cake table, the presents waited in a glittering mountain. Molly had studied the pattern for a week. Two grandmothers guarded the hallway, a hyperactive beagle patrolled the kitchen, and the birthday boy's father slept in a recliner after his third eggnog. "Ready?" Molly asked. "Born ready," Bill whispered, adjusting his reindeer-antler balaclava. "Only problem is the cake." "What about the cake?" "I'm allergic to frosting, and that cake is wall-to-wall buttercream." Molly sighed. Bill nodded solemnly, though he had clearly never once considered a plan without snacks. He tucked a napkin into his pocket, just in case, and checked the zipper of his duffel bag, which rattled ominously with what sounded like dozens of squeaky toys. Somewhere inside, the clown shrieked with laughter. Molly tucked a bag of rubber ducks under her arm and slipped out into the snow, the plan already unraveling beautifully.
created_at
"2026-10-08T08:36:14.28Z"
10/8/2026, 8:36:14 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
12847
moderation_latency
(null)
generation_time
12847
tokens_prompt
75
tokens_completion
341
native_tokens_prompt
95
native_tokens_completion
2611
native_tokens_completion_images
(null)
native_tokens_reasoning
2117
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
0.001315
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448574-puaShspTdJvlLTHHUImW"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448574-8tVkdjAyZtOl6uBdPY1I"
upstream_id
"msg_011CfpTuoP49vHRHtn3CByFs"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTuoP49vHRHtn3CByFs"
is_byok
false
latency
747
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.001315
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
81.27%
Matches word count
n/a
neededClean
false
words
212
99.99%
Dialogue to Total Word Ratio
Ratio: 11.06%, Deviation: 1.06%
neededClean
false
wordsTotal
217
wordsDialogue
24
90.6300%