NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSJTZDGKQ8KQS0E6BJZWYC6
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.9s
Cost:
$0.015515
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 hedge, binoculars trained on the bouncy castle wobbling in the suburban backyard. Crepe-paper streamers sagged between the gutters, and a sad clown twisted balloons into shapes that resembled neither animals nor dignity. The present table, however, gleamed like treasure in a pirate's fevered dream: stacks of glittering boxes, ribbons curling invitingly. Bill adjusted his stolen party hat, the elastic biting cruelly into his stubbled chin. He'd insisted the disguise was foolproof, though he stood a full head taller than every parent present and smelled faintly of cigarettes and regret. "The cake's our distraction," Molly whispered, sketching a diagram in the dirt with a twig. He nodded solemnly, studying the crude map as though it contained the secrets of the universe. Their plan hinged on chaos—specifically, the chaos generated by twelve sugar-addled seven-year-olds released simultaneously toward a piñata. Molly outlined the extraction route: snatch the gifts during the candle-blowing, exit through the gate, vanish into the minivan idling out front. Simple. Elegant. Beneath them, certainly, but rent was rent. Bill cracked his knuckles, eyeing a particularly enormous box wrapped in dinosaur paper. "That one's mine," he murmured greedily. Somewhere inside, a child began wailing. Showtime.
created_at
"2026-05-29T10:00:21.689Z"
5/29/2026, 10:00:21 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3751
moderation_latency
(null)
generation_time
10868
tokens_prompt
77
tokens_completion
401
native_tokens_prompt
93
native_tokens_completion
602
native_tokens_completion_images
(null)
native_tokens_reasoning
54
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
0.015515
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01TNtg8aSzReBvbXC15fnzXd"
is_byok
false
latency
1601
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-1780048821-ac1VeMH8EKNPpVedQgpT"
session_id
(null)
api_type
"completions"
id
"gen-1780048821-zONxtt6Re7QxPXU59nUt"
upstream_id
"msg_01TNtg8aSzReBvbXC15fnzXd"
total_cost
0.015515
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
199
83.01%
Dialogue to Total Word Ratio
Ratio: 3.43%, Deviation: 6.57%
neededClean
false
wordsTotal
204
wordsDialogue
7
91.5063%