NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSKD3AZ2FV9SCQG2J4D55QA
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.6s
Cost:
$0.015340
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
87.09%
Dialogue to Total Word Ratio
(details)
93.5366%
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 hydrangea bush, binoculars pressed to her face, surveying the suburban battlefield ahead. Streamers sagged from the gutters like surrender flags, and a bouncy castle wobbled menacingly in the breeze. Somewhere inside that pastel fortress lay their prize: a glittering mountain of wrapped presents, each one ripe for liberation. Bill adjusted his clown wig, which itched terribly, and consulted the crayon-drawn map he'd stolen from the birthday boy's bedroom window. The plan was elegant in its stupidity. They would infiltrate during the piƱata frenzy, when sugar-crazed children swung blindfolded bats and parental supervision evaporated entirely. "This is foolproof," Molly whispered confidently. He nodded, sweating beneath the polyester. A toddler wielding a juice box eyed him suspiciously from the fence line, ketchup smeared across her cheeks like war paint. Bill held his breath. The toddler blinked, then waddled away, momentarily distracted by a balloon. Molly synchronized her watch, which was actually just a friendship bracelet she'd found earlier. The face-painting station provided perfect cover. Nobody questioned two adults dressed as deranged circus performers at a children's party, after all. That was the genius of it. "Remember," Bill muttered grimly, "no eating the cake." She crossed her fingers behind her back.
created_at
"2026-05-29T10:10:15.527Z"
5/29/2026, 10:10:15 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3277
moderation_latency
(null)
generation_time
11528
tokens_prompt
77
tokens_completion
414
native_tokens_prompt
93
native_tokens_completion
595
native_tokens_completion_images
(null)
native_tokens_reasoning
62
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
0.01534
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01W8tzQpTENo4pzD2Lht5tNH"
is_byok
false
latency
1122
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-1780049415-DbdGhIxqIE3IjoLy153w"
session_id
(null)
api_type
"completions"
id
"gen-1780049415-xSc8VgZb2YpVnEZ3W4aJ"
upstream_id
"msg_01W8tzQpTENo4pzD2Lht5tNH"
total_cost
0.01534
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
87.09%
Dialogue to Total Word Ratio
Ratio: 3.90%, Deviation: 6.10%
neededClean
false
wordsTotal
205
wordsDialogue
8
93.5366%