NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DAG8B8MB32W1C2PD0H1ZAM
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.6s
Cost:
$0.000221
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
1.04%
Matches word count
(details)
77.27%
Dialogue to Total Word Ratio
(details)
39.1508%
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, so the plan," Molly whispered, tapping the blueprint. "We go in through the chimney." "Molly, the chimney's where the clown is." "Which is why we bring the balloon animals. Clowns love balloon animals." "That's not a plan, that's a bribe with extra steps." "Fine. Then you distract the bouncy castle lady." "Why would I distract the bouncy castle lady?" "Because she's got the whole guest list, and I need her to think you're her cousin Derek." "I've never met a cousin named Derek." "Exactly. Nobody's ever checked." "What about the kids? Won't they notice two adults sneaking in with sacks?" "Bill, they're five. They'll think we're magicians." "Magicians don't have crowbars." "Magicians have very strong wrists. Now, the piñata. We lure it out, grab the presents as they fall." "Molly, that piñata's full of candy. Nobody's getting presents." "Then we steal the candy. Presents later." "You're making this worse." "Shh. Someone's coming. Quick, hide behind the cake." "Molly, that's a giant cake shaped like a unicorn." "Then we're definitely hiding behind a unicorn."
created_at
"2026-10-08T08:36:28.656Z"
10/8/2026, 8:36:28 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3553
moderation_latency
(null)
generation_time
3553
tokens_prompt
75
tokens_completion
284
native_tokens_prompt
95
native_tokens_completion
423
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
0.000221
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448588-zs1ywZpFcN1hhtqDk6rx"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448588-8kBCGKTAlW08vbWJ4z96"
upstream_id
"msg_011CfpTvs1ccmbwSxsEdHVsX"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTvs1ccmbwSxsEdHVsX"
is_byok
false
latency
787
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.000221
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
1.04%
Matches word count
n/a
neededClean
false
words
174
77.27%
Dialogue to Total Word Ratio
Ratio: 97.13%, Deviation: 7.13%
neededClean
false
wordsTotal
174
wordsDialogue
169
39.1508%