NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4D9YC06T3C2M83GAP2N3NBS
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.5s
Cost:
$0.000954
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
9.61%
Matches word count
(details)
79.65%
Dialogue to Total Word Ratio
(details)
44.6313%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 crouched behind the hedge, peering at the glowing windows of number twelve. Balloons bobbed against the glass. Somewhere inside, a clown was losing an argument with a bouncy castle. "Right," whispered Bill, adjusting his ski mask over his bald head. "Plan's simple. We slip in during cake, grab the presents, and vanish." "Simple," Molly said flatly. "You said that about the bank." "The bank was a learning experience." "The bank had a security dog, Bill. Dressed as a bee." "Bees are scary." He pulled a sack from his coat, stitched with the words *Lucky Bag*. "I brought extra room for the bigger boxes." "Those boxes are for a seven-year-old's birthday." "Exactly. Think of the loot. Trains. Walkie-talkies. One of those chocolate fountains." "Bill, that's a child's whole afternoon you're talking about." "And he'll get over it by Tuesday. Trust me." Molly sighed and tugged her gloves tighter. "Fine. But if a single child asks who we are, you do the talking." "Deal," Bill said, then tripped over a garden gnome, which let out a loud, cheerful laugh.
created_at
"2026-10-08T08:26:42.579Z"
10/8/2026, 8:26:42 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
9438
moderation_latency
(null)
generation_time
9438
tokens_prompt
75
tokens_completion
274
native_tokens_prompt
95
native_tokens_completion
1888
native_tokens_completion_images
(null)
native_tokens_reasoning
1471
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
0.0009535
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448002-Y7KbR32UhmioYSHdTDJ7"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448002-SvFVET7grnh28GdWNcZb"
upstream_id
"msg_011CfpTBf2bE6tF7JWEihtJy"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTBf2bE6tF7JWEihtJy"
is_byok
false
latency
712
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0009535
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
9.61%
Matches word count
n/a
neededClean
false
words
178
79.65%
Dialogue to Total Word Ratio
Ratio: 56.91%, Deviation: 6.91%
neededClean
false
wordsTotal
181
wordsDialogue
103
44.6313%