NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DABT3DVPTEK2ZNV4S622EY
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.9s
Cost:
$0.001159
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
99.98%
Dialogue to Total Word Ratio
(details)
90.6287%
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
The van idled behind the community hall, headlights off, engine wheezing like a retired accordion. Molly pressed her nose to the window and studied the banner glowing above the side door: HAPPY SEVENTH BIRTHDAY, OLIVER! Bill cracked his knuckles. "Kitchen door. Grab the presents. Leave." Across the lawn, a bouncy castle shuddered to life, sighing as it filled with air. Molly pulled on a fake moustache and a neon vest reading PARTY SAFETY, then checked her reflection and sighed. She looked like a traffic cone wearing a moustache. "Perfect disguise," Bill said. "Don't encourage me." They slipped out of the van and crept toward the kitchen window. Inside, a clown was honking a horn in what sounded like a fierce argument with a toddler. Molly checked her watch. Forty minutes until the piƱata, plenty of time to empty the gift table. The pile of presents looked suspiciously heavy, as if it contained bricks wrapped in Spider-Man paper. Bill reached for the back door handle, then froze. A small sign hung beside it: CAUTION, TODDLER AMBUSH ZONE. "Oh, come on," Molly whispered. "Nobody's ever been ambushed by a toddler."
created_at
"2026-10-08T08:34:02.999Z"
10/8/2026, 8:34:02 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3200
moderation_latency
(null)
generation_time
11890
tokens_prompt
75
tokens_completion
485
native_tokens_prompt
95
native_tokens_completion
2300
native_tokens_completion_images
(null)
native_tokens_reasoning
1857
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
0.0011595
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448443-lexataH7yuJz42NZ7nOR"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448443-q6PPtfj51odq9ymsHX1M"
upstream_id
"msg_011CfpTk8DMZHVsLersLBGHC"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTk8DMZHVsLersLBGHC"
is_byok
false
latency
772
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0011595
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
81.27%
Matches word count
n/a
neededClean
false
words
188
99.98%
Dialogue to Total Word Ratio
Ratio: 11.11%, Deviation: 1.11%
neededClean
false
wordsTotal
189
wordsDialogue
21
90.6287%