NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXBQMKNE0N8G9R4NQ00VR1
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.3s
Cost:
$0.014590
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
83.01%
Dialogue to Total Word Ratio
(details)
91.5063%
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
Molly crouched behind the shrubbery, binoculars trained on the suburban fortress decorated with balloons and a sagging banner that read HAPPY BIRTHDAY TIMMY. Bill wedged himself beside her, crushing a garden gnome with his considerable backside, and offered no apology to the ceramic casualty. The intelligence had been impeccable. Forty children, one distracted clown, and a mountain of gift-wrapped treasure piled beside a bouncy castle that wobbled like a drunken jellyfish. Years of planning bank vaults and museum galleries had led them, somehow, to this. "We strike at piƱata," Molly whispered, eyes gleaming with criminal ambition. Bill nodded gravely, adjusting the foam party hat that constituted his entire disguise. He'd insisted it made him invisible. It did not. The plan was elegant in its simplicity. During the chaos of swinging bats and showering candy, they would slip past the parents, commandeer the wagon overflowing with presents, and vanish into the cul-de-sac before anyone noticed two grown adults fleeing with a child's loot. Molly synchronized their watches, which were actually just identical novelty wristbands she'd found at the dollar store. Professionalism, she believed, lived in the details. "Remember," she breathed, "no mercy." Bill, weeping slightly, pointed at the cake. He was hungry.
created_at
"2026-05-31T11:40:28.704Z"
5/31/2026, 11:40:28 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2736
moderation_latency
(null)
generation_time
11259
tokens_prompt
77
tokens_completion
413
native_tokens_prompt
93
native_tokens_completion
565
native_tokens_completion_images
(null)
native_tokens_reasoning
69
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
0.01459
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_011D26Acme5M6UqtScYxK9H7"
is_byok
false
latency
1137
model_permaslug
"anthropic/claude-4.8-opus-20260528"
provider_name
"Anthropic"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer
(null)
request_id
"req-1780227628-8S0cMj49nfx62ufNoJxv"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780227628-mp1mATQqApCxEq3mhRNf"
upstream_id
"msg_011D26Acme5M6UqtScYxK9H7"
total_cost
0.01459
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
201
83.01%
Dialogue to Total Word Ratio
Ratio: 3.43%, Deviation: 6.57%
neededClean
false
wordsTotal
204
wordsDialogue
7
91.5063%