NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1G8A0GK6BZ4MXGVKA2ZPER
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.2s
Cost:
$0.014815
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
94.99%
Dialogue to Total Word Ratio
(details)
96.3078%
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 wobbling in the suburban backyard. Streamers sagged from the gutters, and a clown honked his nose at children who plainly despised him. Beside her, Bill unfolded a laminated map of the patio furniture, sweating through a stolen caterer's uniform two sizes too small. "The presents are stacked by the piƱata," Molly whispered, jabbing a finger at a glittering mountain of wrapped boxes. Bill nodded gravely, producing a grappling hook better suited to scaling a battleship than a six-foot garden fence. He'd also packed three smoke bombs, a crowbar, and an alarming quantity of confetti, reasoning that nobody suspects a thief who arrives celebrating. The plan was elegant in theory. Molly would create a diversion by challenging the clown to a balloon-animal duel, drawing the parents into a betting frenzy. Bill, meanwhile, would belly-crawl across the lawn beneath a tactical tablecloth, loading gift bags into a wagon disguised as party favors. "What about the dog?" Bill asked, eyeing a sleeping golden retriever. Molly smiled, withdrawing a packet of deli ham from her jacket. They had thought of everything. Everything except the birthday boy, who was now staring directly at them, holding a water pistol with terrifying confidence.
created_at
"2026-06-01T11:49:08.248Z"
6/1/2026, 11:49:08 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4048
moderation_latency
(null)
generation_time
12214
tokens_prompt
77
tokens_completion
383
native_tokens_prompt
93
native_tokens_completion
574
native_tokens_completion_images
(null)
native_tokens_reasoning
44
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_01SVrp7y59hM3ecUJ1HeeTMe"
is_byok
false
latency
1870
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-1780314548-v9sGVZSz64UhInbFIbxd"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780314548-xn5mKfw09FjszofgrDin"
upstream_id
"msg_01SVrp7y59hM3ecUJ1HeeTMe"
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
97.63%
Matches word count
n/a
neededClean
false
words
207
94.99%
Dialogue to Total Word Ratio
Ratio: 5.24%, Deviation: 4.76%
neededClean
false
wordsTotal
210
wordsDialogue
11
96.3078%