NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXA3AHWDETV42TPE2MM53V
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.9s
Cost:
$0.015140
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
82.23%
Dialogue to Total Word Ratio
(details)
90.4713%
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 trained on the bouncing castle while Bill struggled to fit his enormous frame into a stolen clown costume two sizes too small. The seams groaned in protest. Across the lawn, a swarm of seven-year-olds orbited a folding table piled high with glittering, ribbon-wrapped treasure, each present a small fortune of unopened plastic and goodwill. "The cake's the diversion," Molly whispered. Bill nodded, honking his red nose accidentally and freezing as a toddler turned to stare. She had calculated everything: the piƱata would burst at precisely three o'clock, releasing a candy avalanche that would send the children into a feeding frenzy, leaving the gift table gloriously unguarded. They would swoop in, load the loot into Bill's oversized juggling sack, and waddle to the getaway minivan disguised as the entertainment. The plan was flawless, ignoring the minor detail that Bill was allergic to face paint and his cheeks had begun swelling like overripe tomatoes. Molly handed him an antihistamine, which he swallowed dryly, eyes watering. A mother approached, clipboard in hand, suspicious of the two adults lurking near the shrubbery. Molly plastered on a grin. "We're the magicians," she lied smoothly. Bill, sweating profusely, attempted a magic trick and dropped everything.
created_at
"2026-05-31T11:39:35.133Z"
5/31/2026, 11:39:35 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4480
moderation_latency
(null)
generation_time
12865
tokens_prompt
77
tokens_completion
395
native_tokens_prompt
93
native_tokens_completion
587
native_tokens_completion_images
(null)
native_tokens_reasoning
48
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
0.01514
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01VrcrXNf9miGygNjApy216J"
is_byok
false
latency
2446
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-1780227575-1KrfyAqQH8IDW53158eG"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780227575-mTgmQNzb1sb6PUojuZ3g"
upstream_id
"msg_01VrcrXNf9miGygNjApy216J"
total_cost
0.01514
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
206
82.23%
Dialogue to Total Word Ratio
Ratio: 3.35%, Deviation: 6.65%
neededClean
false
wordsTotal
209
wordsDialogue
7
90.4713%