NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-09-01M4G0WPSC7A88VJBKWFEDJJV9
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
13.4s
Cost:
$0.001271
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
0.03%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
50.0123%
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 getaway van idled behind a bouncy castle warehouse, headlights off, engine coughing like a retired accordion. Molly pressed her face to the window and squinted across the lawn. Fairy lights glowed over a party tent, and beside a towering cake shaped like a castle sat a mountain of wrapped presents, each one tagged with a name and a tiny drawing of a dinosaur. Bill unfolded the blueprints across his knees. Someone had doodled a grinning clown in the margin, and he had decided to ignore it. "Security?" Molly whispered. "One dad, asleep in a deckchair," Bill said. "Holding a sausage roll like a teddy bear." Molly tugged a pink ski mask over her head, complete with a stitched unicorn horn. She checked her pockets: lockpicks, duct tape, three chocolate coins, and a whistle she could not remember stealing. They crept across the damp grass, sneakers squelching in something neither wanted to identify. Bill clutched a sack large enough to hold a small pony and muttered instructions to himself about not sneezing near the balloons. The tent flap opened easily. Inside, a dozen children slept in sleeping bags shaped like sharks and unicorns. Molly tiptoed between them, grabbed the nearest box, and grinned. A tiny voice piped up from the darkness. "Are you the present thieves?" Molly froze. Bill slowly lowered his sack. "No," he whispered. "We're the present people."
created_at
"2026-10-09T09:46:14.194Z"
10/9/2026, 9:46:14 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2815
moderation_latency
(null)
generation_time
13340
tokens_prompt
75
tokens_completion
637
native_tokens_prompt
95
native_tokens_completion
2523
native_tokens_completion_images
(null)
native_tokens_reasoning
2019
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
0.001271
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791539174-xhJknpPrBlGoeJ58EDXI"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791539174-ohXyPKyFWBL5cnLsN0fm"
upstream_id
"msg_011CfrT4K6r71pXM2bAeTUBm"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfrT4K6r71pXM2bAeTUBm"
is_byok
false
latency
730
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.001271
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
0.03%
Matches word count
n/a
neededClean
false
words
230
99.99%
Dialogue to Total Word Ratio
Ratio: 10.87%, Deviation: 0.87%
neededClean
false
wordsTotal
230
wordsDialogue
25
50.0123%