NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DAE55ZBGFH59VCAJ8WSSG2
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
16.1s
Cost:
$0.001836
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
99.79%
Dialogue to Total Word Ratio
(details)
99.5845%
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 row of wilted hedges, headlights off for maximum sneakiness. Molly crouched by the bumper, peering through binoculars at the bouncy castle glowing in the backyard of number 14 Maple Drive. Balloons bobbed. Somewhere, a clown was shrieking the rules of musical chairs. Beside her, Bill adjusted his ski mask, which had been designed for a much smaller man. He patted his coat pocket, where a crowbar and a sack of jelly beans clinked together. "Is the security really a golden retriever?" he whispered. "Bribe him with a sausage roll." Bill sighed. Across the lawn, a parent in a sensible cardigan waved at the empty street. Molly waved back, then tugged his sleeve. Together they slipped through the side gate, past a mountain of scooters and a sign reading "Shoes Off, Please!" Bill removed his boots with dignity. Molly did not. The back door was unlocked, because of course it was. Inside, presents towered on a folding table, wrapped in paper covered with dinosaurs and sparkly unicorns. Molly rubbed her gloved hands together. "Grab the big ones." Bill was already stuffing a pony-shaped box into his sack. He stared at the label, then at Molly. "Molly, this one's a bicycle."
created_at
"2026-10-08T08:35:19.88Z"
10/8/2026, 8:35:19 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
16040
moderation_latency
(null)
generation_time
16040
tokens_prompt
75
tokens_completion
309
native_tokens_prompt
95
native_tokens_completion
3653
native_tokens_completion_images
(null)
native_tokens_reasoning
3199
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
0.001836
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448519-3wsOymipuVfVJYwwdfmt"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448519-c0Ae92GuTUJGGQMOiDol"
upstream_id
"msg_011CfpTqnoDei8Te2bs4QfYY"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTqnoDei8Te2bs4QfYY"
is_byok
false
latency
837
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.001836
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
99.38%
Matches word count
n/a
neededClean
false
words
205
99.79%
Dialogue to Total Word Ratio
Ratio: 12.14%, Deviation: 2.14%
neededClean
false
wordsTotal
206
wordsDialogue
25
99.5845%