NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DAEP6A0BXBMRB6EE1AW448
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.2s
Cost:
$0.000183
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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 tapped the blueprint pinned to the van's dashboard. "The party's in the Hendersons' backyard, third house past the oak. Forty-two presents, according to the invitation." Bill squinted at the sketch of the bouncy castle. "Why is there a castle in our plan?" "Because it's a distraction. Nobody notices a thief when a seven-year-old is screaming down a slide." "Right. And the clown?" "Ignore the clown. He's the one who sold us the map." Bill nodded slowly, then pulled a rubber mask over his face. It was shaped like a grinning sheep. "Do I look intimidating?" "You look like a sheep who's lost his mind." "Good. Fear is half the job." They slipped out of the van, carrying a canvas sack big enough to hold a small pony. Somewhere a birthday song began, off-key and enthusiastic. Molly sighed. "Remember, no candy. We're professionals." "Professionals," Bill whispered, already eyeing the cupcakes.
created_at
"2026-10-08T08:35:37.298Z"
10/8/2026, 8:35:37 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
729
moderation_latency
(null)
generation_time
3174
tokens_prompt
75
tokens_completion
233
native_tokens_prompt
95
native_tokens_completion
348
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.0001835
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448537-9N7vFFDAX17NaU9BuYxA"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448537-QIhCEKa1Dk5HKfDKMU1A"
upstream_id
"msg_011CfpTs5Z4VUMsWKPVji8Rm"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTs5Z4VUMsWKPVji8Rm"
is_byok
false
latency
729
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0001835
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
0.00%
Matches word count
n/a
neededClean
false
words
150
0.00%
Dialogue to Total Word Ratio
Ratio: 54.55%, Deviation: 44.55%
neededClean
false
wordsTotal
154
wordsDialogue
84
0.0000%