NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DAKK8QR4XK0WD9SNNM53MV
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.0s
Cost:
$0.000166
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, here's the plan. We slip in through the bouncy castle, nobody notices a shadow in a bouncy castle." "Molly, the bouncy castle has a clown in it. He's been staring at me since we parked." "Ignore the clown. Next, we grab the presents from the table by the cake." "The cake's got a lot of candles on it, Molly. Who puts that many candles on a cake?" "A seven-year-old's mum, that's who. Now, the big pile is in the corner. Blue wrapping, yellow bows. Those are the good ones." "How do you know which ones are good?" "The label says 'From Auntie Pam, £50 Voucher.' Trust me, Bill." "Fine. And what if a kid spots us?" "Then you smile, offer him a balloon, and say the magic words." "What magic words?" "Pass the parcel, sunshine. Now move, before the music stops."
created_at
"2026-10-08T08:38:18.143Z"
10/8/2026, 8:38:18 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2998
moderation_latency
(null)
generation_time
2998
tokens_prompt
75
tokens_completion
202
native_tokens_prompt
95
native_tokens_completion
312
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
0.0001655
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448698-KvvKljwXgx8dFHqL4lYP"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448698-u5WkXLRIKEX2vUqmY0F4"
upstream_id
"msg_011CfpU4wB7vEBd1wD8WPdha"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpU4wB7vEBd1wD8WPdha"
is_byok
false
latency
812
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0001655
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
143
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
145
wordsDialogue
145
18.3940%