NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXRY56PGDZEDYD2KW5T5B2
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.6s
Cost:
$0.012590
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
72.27%
Dialogue to Total Word Ratio
(details)
86.1345%
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 bouncy castle, binoculars trained on the gift table. Mountains of glittering packages glistened under the afternoon sun, guarded by nothing more menacing than a clown twisting balloons into wiener dogs. "Easy money," she whispered. Bill, squeezed into a costume two sizes too small, adjusted his enormous foam dinosaur head. The zipper dug into his spine. He'd argued for the magician disguise, but Molly insisted dinosaurs blended better at a six-year-old's birthday bash. The plan was elegant in its simplicity. Bill would lumber through the crowd, distracting the children with theatrical roars while Molly, disguised as the entertainment coordinator, loaded the presents into a wagon she'd painted to resemble a party prop. They'd be gone before anyone unwrapped a single bow. A child wielding a juice box wandered dangerously close to their hiding spot. Bill froze, holding his breath inside the suffocating costume. "Stay calm," Molly mouthed. The toddler studied the dinosaur suspiciously, then offered Bill a half-eaten cookie. He accepted it with a trembling claw. Across the lawn, the birthday boy's mother announced cake time. The crowd surged toward the house, leaving the treasure unguarded. Molly grinned, gripping her wagon handle. "Showtime." Bill roared, and chaos commenced.
created_at
"2026-05-31T11:47:41.364Z"
5/31/2026, 11:47:41 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
984
moderation_latency
(null)
generation_time
9509
tokens_prompt
77
tokens_completion
347
native_tokens_prompt
93
native_tokens_completion
485
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
0.01259
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01X9u1Mv348u8Hu4m1VXNNNE"
is_byok
false
latency
984
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-1780228061-7uWJxd4Vyuw61naeyiTd"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780228061-O07tf4tnKOC9N43JrByP"
upstream_id
"msg_01X9u1Mv348u8Hu4m1VXNNNE"
total_cost
0.01259
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
72.27%
Dialogue to Total Word Ratio
Ratio: 2.45%, Deviation: 7.55%
neededClean
false
wordsTotal
204
wordsDialogue
5
86.1345%