NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1G7QFX735DXFENB5E3V09Y
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.6s
Cost:
$0.015165
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
65.47%
Dialogue to Total Word Ratio
(details)
82.7329%
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 as it wobbled menacingly in the suburban breeze. Beside her, Bill unfolded a hand-drawn map of the backyard, complete with a skull-and-crossbones sticker marking the gift table. "Twelve presents, minimum," Molly whispered, counting through the lenses. Bill nodded gravely, smearing a smudge of birthday-cake-scented camouflage across his cheeks. The clown had arrived ten minutes ago, and chaos was their ally now—shrieking children orbited the piñata like tiny, sugar-fueled satellites, and not one adult had glanced toward the perimeter fence. They had rehearsed this for weeks in Bill's garage, practicing on his nephew's action figures until they could clear a table in under nine seconds. The plan was elegant: distraction, extraction, escape through the gap behind the garden gnomes. Molly tightened the straps on her oversized swag bag, which she'd cleverly disguised as a present, complete with a lopsided bow. A toddler in a dinosaur costume waddled directly into their line of sight, regarding them with unsettling suspicion. "Abort," Bill hissed. But Molly was already committed, crawling forward through the freshly mowed grass, dodging discarded juice boxes, her heart pounding with the reckless thrill of professional, absurdly committed criminals everywhere.
created_at
"2026-06-01T11:48:49.285Z"
6/1/2026, 11:48:49 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3246
moderation_latency
(null)
generation_time
10544
tokens_prompt
77
tokens_completion
390
native_tokens_prompt
93
native_tokens_completion
588
native_tokens_completion_images
(null)
native_tokens_reasoning
41
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
0.015165
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_014NS7jAbhB8VK4TiMgeZSX1"
is_byok
false
latency
1130
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-1780314529-rLMc0RwxbRvAcgdFal4D"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780314529-rYcdgi0QFIQI9yNnTgGR"
upstream_id
"msg_014NS7jAbhB8VK4TiMgeZSX1"
total_cost
0.015165
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
65.47%
Dialogue to Total Word Ratio
Ratio: 1.93%, Deviation: 8.07%
neededClean
false
wordsTotal
207
wordsDialogue
4
82.7329%