NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DZJBJQGMH7ECMQYXPZCFWJ
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3m 4s
Cost:
$0.023914
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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
Molly and Bill crouched behind a privet hedge, eyeing the glowing windows of number 14 Maple Lane. Through the conservatory glass, thirty sugar-crazed children shrieked around a bouncy castle while a magician in a banana costume lost a wrestling match with a unicycle. Molly tapped a plan drawn on a pizza box, her red foam nose askew. "Ten minutes. Every present. No witnesses." Bill nodded solemnly, then sneezed into his fake moustache, which launched itself into the hedge. He retrieved it with dignity, then tiptoed toward the gate in squeaky clown shoes. Every step sounded like a dying goose. "What about the banana?" Molly shrugged. "Who's going to believe a banana?" The plan was simple. Pose as the hired clowns, hoist the gifts into a wheelbarrow beneath a tarpaulin marked PARTY SUPPLIES, and vanish before anybody cut the cake. Bill squinted at the wheelbarrow, which had one flat tyre, a suspicious wobble, and jam on the handles. Molly sighed. "Still, it works. Mostly." Through the living room window, presents towered beside an empty sofa, wrapped in glittering paper and labelled in crayon. One box, marked FROM AUNTIE DOT, had air holes. Molly decided that was a problem for Future Molly.
created_at
"2026-10-08T14:44:37.603Z"
10/8/2026, 2:44:37 PM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2453
moderation_latency
(null)
generation_time
183693
tokens_prompt
75
tokens_completion
6314
native_tokens_prompt
95
native_tokens_completion
47808
native_tokens_completion_images
(null)
native_tokens_reasoning
47330
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
0.0239135
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791470677-pQkjFAnfIOO8PKxevl0F"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791470677-OJeD14SVcJ352JCYx9xd"
upstream_id
"msg_011Cfpx19K1vA58MpGheBg7V"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011Cfpx19K1vA58MpGheBg7V"
is_byok
false
latency
872
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0239135
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
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 9.95%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
20
100.0000%