NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSK87MHFXAYK33F8BYPM4WV
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
12.4s
Cost:
$0.012415
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.8726%
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 spread the blueprint across the table, tapping a finger on the bouncy castle. "The presents pile up here, right next to the piƱata," she said. "We grab everything during cake time." Bill frowned, scratching his chin. "Cake time? You want us to rob a seven-year-old?" "Not just one. There'll be twenty kids. That's twenty presents, minimum." "And what's our exit strategy?" Molly grinned. "We dress as clowns. Nobody questions clowns." "I hate clowns," Bill muttered. "They're terrifying." "Exactly. The parents won't look too closely, and the kids will be too scared to chase us." Bill leaned back, arms crossed. "What about security?" "Security?" Molly laughed. "It's a birthday party, not Fort Knox. The biggest threat is a golden retriever named Biscuit." "Biscuit could be dangerous." "Biscuit is fourteen and blind in one eye." Bill considered this, then nodded slowly. "Fine. But I'm not doing balloon animals. I refuse." "You'll do whatever sells the disguise." "I draw the line at balloon animals, Molly." She slid a red foam nose across the table toward him. "You'll make a lovely poodle." Bill stared at the nose like it had personally insulted him. "This," he sighed, picking it up, "is the lowest point of my criminal career."
created_at
"2026-05-29T10:07:36.089Z"
5/29/2026, 10:07:36 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4296
moderation_latency
(null)
generation_time
12350
tokens_prompt
77
tokens_completion
340
native_tokens_prompt
93
native_tokens_completion
478
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
0.012415
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01NbhowPEdHsfJAV3M7a2xZo"
is_byok
false
latency
4239
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-1780049256-7CC5uwzTlQnEvHstNokv"
session_id
(null)
api_type
"completions"
id
"gen-1780049256-XPDhqgU0S3fII8GTZxyl"
upstream_id
"msg_01NbhowPEdHsfJAV3M7a2xZo"
total_cost
0.012415
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
0.00%
Dialogue to Total Word Ratio
Ratio: 68.45%, Deviation: 18.45%
neededClean
false
wordsTotal
206
wordsDialogue
141
49.8726%