NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DA8X0GDCBAS4516ZAM1M9Y
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.4s
Cost:
$0.000196
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
18.3940%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"Right, Bill, listen. The party's at number twelve, Maple Crescent. Nine kids, one clown, and a mountain of presents in the front room." "A clown? Molly, I hate clowns." "Nobody likes clowns, Bill. That's why we bring the balloon animals. Distraction." "Balloon animals? Where are we getting balloon animals?" "I made them. Four giraffes and a poodle. Don't ask." "Fine. And the back door?" "Unlocked. Mrs. Pritchard always leaves it open for the cat." "What about the dog?" "There's no dog. There's a hamster. Very small, very scary, I'm told." "Molly, a hamster isn't a security system." "Then you go in first and tell it that." "And what do we do with nine presents?" "Ten, Bill. The birthday girl's gift is mine." "That's not how this works." "It's exactly how this works. Now, have you got the sack?" "I've got a pillowcase." "Close enough. Let's go be the worst-behaved guests in the history of Maple Crescent."
created_at
"2026-10-08T08:32:27.673Z"
10/8/2026, 8:32:27 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
929
moderation_latency
(null)
generation_time
3315
tokens_prompt
75
tokens_completion
242
native_tokens_prompt
95
native_tokens_completion
372
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
0.0001955
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448347-j9T9jG3cQLGfZ7Fwf6gn"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448347-ZWZIWjRHZN0O22eAlVFo"
upstream_id
"msg_011CfpTd7R3GGd1dz8HNETEt"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTd7R3GGd1dz8HNETEt"
is_byok
false
latency
929
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0001955
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
156
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
157
wordsDialogue
157
18.3940%