NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DAFW2FW6VX9JMNF3C9CMCT
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.9s
Cost:
$0.000167
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
26.42%
Dialogue to Total Word Ratio
(details)
13.2123%
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 rented bouncy castle, peering at the backyard through a gap in the balloons. "Eight kids, one clown, and a pile of presents the size of a fridge," she whispered. "Tell me again why we're robbing a seven-year-old's birthday?" Bill adjusted his fake mustache, which kept drooping like a wilted noodle. "Because Gerald said the loot is gift-wrapped in gold foil. Gold foil, Molly. Think of the resale value." "Gerald also said the clown was retired." "He's not a clown. He's a sad mime with a whistle." Molly groaned. "Fine. You grab the blue box, I'll handle the pink one. Quietly." "Quietly," Bill agreed, then tripped over a garden gnome and crashed into the cake table. Somewhere, a child screamed, "THIEVES!" Molly sighed. "Well. That went about as planned."
created_at
"2026-10-08T08:36:16.088Z"
10/8/2026, 8:36:16 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2823
moderation_latency
(null)
generation_time
2823
tokens_prompt
75
tokens_completion
202
native_tokens_prompt
95
native_tokens_completion
314
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)
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
0.0001665
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448576-If1IwbqOIuBjCY1sguOJ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448576-n4XWiSUQsBEhQDNIxKEh"
upstream_id
"msg_011CfpTuwWhs6kiBu71NXyYF"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTuwWhs6kiBu71NXyYF"
is_byok
false
latency
763
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0001665
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
0.00%
Matches word count
n/a
neededClean
false
words
132
26.42%
Dialogue to Total Word Ratio
Ratio: 60.74%, Deviation: 10.74%
neededClean
false
wordsTotal
135
wordsDialogue
82
13.2123%