NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSK7ZK7YA9ZAMWBM7ZKTJ6S
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.7s
Cost:
$0.014815
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
78.01%
Dialogue to Total Word Ratio
(details)
88.9994%
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 hydrangeas, binoculars trained on the bouncy castle as if it were Fort Knox with a clown theme. Beside her, Bill unrolled a blueprint that turned out to be a placemat from a pizza restaurant, sauce still glistening on the corner where he'd planned the getaway route. The party raged on. Twelve children, sugar-drunk and feral, swarmed the snack table while a man in a moth-eaten dinosaur costume waved his stubby arms in despair. The pile of presents glittered near the gazebo, wrapped and ribboned, practically begging to be liberated. "That's our score," Bill whispered, dribbling. Molly nodded gravely, sketching a diversion involving a piñata, three water balloons, and what she optimistically labeled "controlled chaos." Their plan hinged on infiltrating disguised as entertainers, though their only costumes were a single mustache and a tambourine. A toddler spotted them, pointed, and screamed with the lung capacity of an air raid siren. Bill froze. Molly considered surrender. "Run," she hissed. They sprinted, the dinosaur giving chase, presents forgotten, dignity shredded somewhere near the petting zoo. Behind a parked minivan they paused, breathless, defeated, and—Bill realized with horror—still clutching nothing but a stolen juice box and someone's abandoned party hat.
created_at
"2026-05-29T10:07:27.855Z"
5/29/2026, 10:07:27 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2569
moderation_latency
(null)
generation_time
10713
tokens_prompt
77
tokens_completion
393
native_tokens_prompt
93
native_tokens_completion
574
native_tokens_completion_images
(null)
native_tokens_reasoning
52
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
0.014815
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_0171RuFHxJam4KTddW7piUc6"
is_byok
false
latency
1002
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-1780049247-9fapFasq4sjPyXbAvuSF"
session_id
(null)
api_type
"completions"
id
"gen-1780049247-78wbf4UkgoKEXfVKIyN6"
upstream_id
"msg_0171RuFHxJam4KTddW7piUc6"
total_cost
0.014815
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
78.01%
Dialogue to Total Word Ratio
Ratio: 2.94%, Deviation: 7.06%
neededClean
false
wordsTotal
204
wordsDialogue
6
88.9994%