NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DAH28DMJTHB9TBZ4KW46TV
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.0s
Cost:
$0.000179
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
84.76%
Dialogue to Total Word Ratio
(details)
42.3797%
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, the plan's simple," Molly whispered, tapping the blueprint. "We slip through the back window while the clown's doing his balloon animals." "Balloon animals? Molly, that clown's terrifying. He looked at me like I owed him money." "Focus, Bill. Three guards, one bouncy castle, and a pile of presents taller than you." "Guards? It's a birthday party, not Fort Knox." "Tell that to Gerald. He's got a whistle and a grudge." "Fine. What's my job?" "You're on lookout. Watch for the mum with the camera." "And if she spots me?" "Smile, wave, say you're here for the jelly." "Nobody's here for the jelly, Molly." "Exactly. Nobody questions a man with jelly." "What about the cake?" "Leave the cake, Bill. We're not monsters." "Speak for yourself. I've eyed that pink frosting all afternoon." "Stop drooling and grab the bag."
created_at
"2026-10-08T08:36:55.19Z"
10/8/2026, 8:36:55 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3001
moderation_latency
(null)
generation_time
3001
tokens_prompt
75
tokens_completion
218
native_tokens_prompt
95
native_tokens_completion
338
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
0.0001785
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448615-ZS4sfZO5i3Hz0ThgS5bJ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448615-WNLsCMUe4qP3t7yhkCKO"
upstream_id
"msg_011CfpTxpMBX6AKZRWwR2E6N"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTxpMBX6AKZRWwR2E6N"
is_byok
false
latency
715
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0001785
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
138
84.76%
Dialogue to Total Word Ratio
Ratio: 96.38%, Deviation: 6.38%
neededClean
false
wordsTotal
138
wordsDialogue
133
42.3797%