NC Bench
Overview
About
Tests
Models
Model
Claude Haiku 4.5
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2026-02-08-01KGYXPV85DV000MWCSXNK91MB
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
Molly adjusted her fake mustache while Bill unfolded the blueprints of Tiny Tots Entertainment Center across the sticky table at their hideout. The plan was audacious, borderline insane, but they'd successfully stolen a Fabergé egg once, so a room full of gift-wrapped boxes seemed manageable. "So we go in through the ball pit?" Bill asked, pointing at the diagram. "Exactly. No one suspects the ball pit," Molly replied. The reconnaissance had taken weeks. They'd learned that Mrs. Henderson's birthday party would feature approximately forty presents ranging from action figures to gaming consoles. It was their biggest score yet, though admittedly their weirdest. Bill practiced his cover story in the mirror: a slightly incompetent party clown named Bobo. Molly would pose as a supply coordinator. Their getaway vehicle, a ice cream truck, was already positioned two blocks away. They reviewed the security footage one more time. The party would reach peak chaos around three o'clock, right when everyone gathered for cake. That's when they'd strike, moving swiftly through the gymnasium, filling their reinforced duffels with merchandise. "This is either our greatest heist or our most embarrassing," Bill muttered. Molly grinned. "Why not both?"
created_at
"2026-02-08T15:25:21.825091+00:00"
Sunday, February 8th, 2026 at 3:25:21 PM GMT+00:00
model
"anthropic/claude-4.5-haiku-20251001"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1235
moderation_latency
185
generation_time
4409
tokens_prompt
61
tokens_completion
251
native_tokens_prompt
75
native_tokens_completion
293
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00154
router
(null)
provider_responses
0
id
"37f5f236-b7a5-4d12-b352-c0c327d9f278"
status
200
is_byok
false
latency
1234
endpoint_id
"d000261c-5aeb-47d1-ac87-ad64dbe1cdb6"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.5-haiku-20251001"
api_type
"completions"
id
"gen-1770564316-vgih7V33DqMeOWohIEnk"
upstream_id
"37f5f236-b7a5-4d12-b352-c0c327d9f278"
total_cost
0.00154
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
97.6276%
Matches word count
n/a
neededClean
false
words
193
95.9551%
Dialogue to Total Word Ratio
Ratio: 14.51%, Deviation: 4.51%
neededClean
false
wordsTotal
193
wordsDialogue
28
96.7913%