NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DY8ECPMBPKG2J39W05T8QW
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3m 47s
Cost:
$0.028601
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9587%
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
Molly unfolded a napkin covered in arrows. "Bill, the magician sprained his wrist in a ball pit, so tonight we're sneaking in as Marvello and his glamorous assistant." Molly tossed him a sequined waistcoat. "Why am I the glamorous one?" "Because you're wearing sequins. Kids can smell fear, so look confident." "And the trick?" "The Vanishing Presents. You wave the wand, I sweep every present into the sack, and nobody notices because they're screaming at the bouncy castle." "What about the little one with the plastic sword?" "Dylan. Six years old, bit his own dad at Christmas. Give him a balloon sword and an extra slice of cake." "Isn't that bribery?" "Crime's mostly bribery, Bill." "And the mum?" "Julia? Gin and a clipboard. Never underestimate a clipboard." Bill's conscience stirred beneath his sequins. "Molly, they're only little." "They've got enough Lego for a second house. They'll survive." "Fine. And the exit?" "Out the back, past the bins. Nobody watches the bins." "And the getaway van?" "Parked behind the bouncy castle." "Why there?" "Nobody looks behind bouncy castles." "And if we get caught?" "We say it was part of the act." "Will they buy that?" "They're six, Bill. They'll believe anything with jazz hands."
created_at
"2026-10-08T14:21:44.229Z"
10/8/2026, 2:21:44 PM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2555
moderation_latency
(null)
generation_time
227197
tokens_prompt
75
tokens_completion
7226
native_tokens_prompt
95
native_tokens_completion
57183
native_tokens_completion_images
(null)
native_tokens_reasoning
56683
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
0.028601
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791469304-XthXDWHnQQN4y9bksE90"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791469304-EMuwEnQQEv0Y9dUY6OBy"
upstream_id
"msg_011CfpvFuF7oNveY2RXTTx5v"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpvFuF7oNveY2RXTTx5v"
is_byok
false
latency
856
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.028601
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
99.92%
Matches word count
n/a
neededClean
false
words
203
100.00%
Dialogue to Total Word Ratio
Ratio: 90.64%, Deviation: 0.64%
neededClean
false
wordsTotal
203
wordsDialogue
184
99.9587%