NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-09-01M4G0DJ8XG3JG7TDMGY71WG7G
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.0s
Cost:
$0.000532
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
45.2419%
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 van idled behind the bouncy castle hire depot, headlights off, its occupants wearing clown wigs they had swiped from a ribbon-cutting ceremony. Molly tapped the blueprints spread across the dashboard. "Third window on the left is the loose one," she whispered. Bill squinted at the sketch, which was mostly a cartoon unicorn with a question mark floating above its head. "And the guard?" "Mrs. Pennywhistle. Sixty-four. Runs the bran muffin stall." Bill nodded gravely and cracked his knuckles, producing a sound like a tiny cereal box popping. Across the car park, the party glowed with fairy lights. Toddlers wobbled past clutching balloons shaped like dinosaurs, and somewhere inside, a birthday cake the size of a tractor tire waited for its candles. Molly checked her watch. "Forty minutes until cake. Then the piñata breaks and every gift gets tossed onto the lawn." Bill grinned and adjusted his fake mustache, which had begun drooping like a wilted lettuce. "So we move during the piñata. Nobody watches the gift table when there's candy flying." They climbed out, moving as silently as ninjas in sneakers that squeaked on every step. Molly stopped and glared at him. "Bill, why are your shoes flashing red?" "They're stealth sneakers," he hissed. "The lights are a distraction."
created_at
"2026-10-09T09:37:58.053Z"
10/9/2026, 9:37:58 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2443
moderation_latency
(null)
generation_time
6022
tokens_prompt
75
tokens_completion
382
native_tokens_prompt
95
native_tokens_completion
1045
native_tokens_completion_images
(null)
native_tokens_reasoning
562
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
0.000532
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791538678-3i2ZCZPVUNVN1WFSY1jM"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791538678-B2e14aSDD7fe71SQA9nZ"
upstream_id
"msg_011CfrSRjkPKjSza761uxMct"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfrSRjkPKjSza761uxMct"
is_byok
false
latency
683
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.000532
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
90.48%
Matches word count
n/a
neededClean
false
words
210
0.00%
Dialogue to Total Word Ratio
Ratio: 31.60%, Deviation: 21.60%
neededClean
false
wordsTotal
212
wordsDialogue
67
45.2419%