NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DA9FRKAJBTTY7XW1X2DM6F
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.9s
Cost:
$0.001021
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
99.88%
Dialogue to Total Word Ratio
(details)
97.9341%
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 van idled behind the bouncy castle hire company, its headlights switched off for dramatic effect. Molly pressed a pair of binoculars to her eyes and surveyed the backyard of number twelve Maple Lane. Balloons bobbed in the breeze. A clown juggled flaming torches with alarming confidence, and somewhere a child shrieked with joy at the sight of a sugar-coated pony. "Four guards," Bill whispered, tapping a clipboard covered in hand-drawn diagrams. "Two dogs. One grandmother." "Grandmother?" "She's guarding the piƱata." Molly lowered the binoculars with a sigh. Their plan had seemed airtight in the kitchen last night, somewhere between the second bottle of wine and the third moustache doodled on the blueprint. Now it looked considerably less brilliant. Bill adjusted his ski mask, which was pink and printed with cartoon unicorns, and nodded with the confidence of a man who had never once been correct. "Nobody suspects a party crew," he said. Molly glanced down at the matching paper hats they were both wearing, each one bright purple and slightly crooked. She hefted the sack labelled "LOOT" in glitter paint and took a deep breath. "Right. Operation Gift Wrap begins now."
created_at
"2026-10-08T08:32:46.877Z"
10/8/2026, 8:32:46 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
8462
moderation_latency
(null)
generation_time
9914
tokens_prompt
75
tokens_completion
302
native_tokens_prompt
95
native_tokens_completion
2023
native_tokens_completion_images
(null)
native_tokens_reasoning
1584
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
0.001021
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448366-gpcUMRbHfUdmTrDTCs4j"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448366-0R1r6ZHsTWxqHDUXWdXU"
upstream_id
"msg_011CfpTeWtT2viJbWwSWv64q"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTeWtT2viJbWwSWv64q"
is_byok
false
latency
733
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.001021
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
95.99%
Matches word count
n/a
neededClean
false
words
192
99.88%
Dialogue to Total Word Ratio
Ratio: 11.86%, Deviation: 1.86%
neededClean
false
wordsTotal
194
wordsDialogue
23
97.9341%