NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4D9XHH26817AFSGMZKQQ5BY
Run Details
Model:
Claude Haiku 5.5 (Adaptive)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.4s
Cost:
$0.000866
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
98.10%
Dialogue to Total Word Ratio
(details)
79.1857%
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, eyeing the glowing windows of number 14 Maple Lane. Balloons bobbed against the porch like captured ghosts. Somewhere inside, a child shrieked with joy, and a juice box exploded with a sharp pop. "Right," Bill whispered, adjusting his fake mustache. "Phase one. We slip past the bouncy castle." "There's a bouncy castle?" "Hundreds of tiny screaming people, Molly. It's a fortress." She sighed and tugged her stolen clown wig into place. "And the presents?" "Stacked by the piano. Forty-two boxes, each with a gold bow. Every one of them wrapped in paper with cartoon dinosaurs." "Why do they need forty-two presents?" "Exactly my point. Greedy little pirates." Molly checked her watch, then glanced at the front door, where a man in a polka-dot suit was juggling three bowling pins. "The clown's starting the magic show in five minutes. That's our window." "Perfect. Once the kids are watching a rabbit come out of a hat, we grab the loot and vanish." "And if someone asks what we're doing?" Bill grinned, pulling a lopsided balloon animal from his pocket. "We're the entertainment."
created_at
"2026-10-08T08:26:15.465Z"
10/8/2026, 8:26:15 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
8367
moderation_latency
(null)
generation_time
8367
tokens_prompt
75
tokens_completion
288
native_tokens_prompt
95
native_tokens_completion
1714
native_tokens_completion_images
(null)
native_tokens_reasoning
1277
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
0.0008665
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791447975-LHdbsTu3uCA2fIqc4LMx"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791447975-sNglm8OQy5rp1k111Mwd"
upstream_id
"msg_011CfpT9fLdwqLQWEQb9sDHy"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpT9fLdwqLQWEQb9sDHy"
is_byok
false
latency
735
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0008665
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
60.28%
Matches word count
n/a
neededClean
false
words
185
98.10%
Dialogue to Total Word Ratio
Ratio: 53.72%, Deviation: 3.72%
neededClean
false
wordsTotal
188
wordsDialogue
101
79.1857%