NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DA5BTSA6VR2BS3M4D8Q6DT
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.3s
Cost:
$0.000880
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
79.56%
Dialogue to Total Word Ratio
(details)
73.8321%
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 through a gap in the bouncy castle at the glowing backyard. "Third window on the left, Bill. Balloons everywhere. Two hundred presents stacked by the piƱata." Bill adjusted his fake mustache. "Are we sure the kids are asleep?" "They're eight. They're on their fourth cupcake and a sugar-fueled dance-off. Nobody's sleeping." "Right. And the clown?" "Distracted. I paid him in glitter and a promise." Molly slid a crowbar from her coat. "Now listen. Blue wrapping paper goes in the van. Anything shaped like a pony goes too. Anything that rattles, we leave. It's probably socks." "Socks are a crime, Molly." Bill nodded solemnly, pulling a stocking over his head with great dignity. "Only when they're disguised as a gift." Bill froze as a small voice squeaked from the patio. "Who are you?" A tiny girl in a princess dress stared at them, clutching a juice box like a weapon. Molly smiled sweetly and lowered her voice, trying her best to sound jolly. "Santa's helpers, sweetheart. Go back to your cake." "Santa doesn't wear a ski mask." "Ssh. Bill, bag. Now."
created_at
"2026-10-08T08:30:31.777Z"
10/8/2026, 8:30:31 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
7093
moderation_latency
(null)
generation_time
8327
tokens_prompt
75
tokens_completion
285
native_tokens_prompt
95
native_tokens_completion
1742
native_tokens_completion_images
(null)
native_tokens_reasoning
1294
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
0.0008805
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448231-A0kq37y0JWjL1onzPcYy"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448231-bUqLNSY8q8mpX5z9BGD0"
upstream_id
"msg_011CfpTUZ5PVhuziPBpFzfd2"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTUZ5PVhuziPBpFzfd2"
is_byok
false
latency
697
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0008805
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
68.10%
Matches word count
n/a
neededClean
false
words
186
79.56%
Dialogue to Total Word Ratio
Ratio: 56.91%, Deviation: 6.91%
neededClean
false
wordsTotal
188
wordsDialogue
107
73.8321%