NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-29-01KSSK95H46023N11Y6MBCYQFM
Run Details
Model:
Claude Opus 4.8 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.0s
Cost:
$0.014365
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
86.79%
Dialogue to Total Word Ratio
(details)
93.2668%
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 struggled into a clown costume three sizes too small, the seams screaming in protest with every movement. The afternoon sun glinted off the mountain of brightly wrapped presents stacked beside a folding table laden with juice boxes and a suspiciously lopsided birthday cake. "This is the big one," Bill whispered, adjusting his rubber nose. She lowered the binoculars and shot him a withering glance, the kind reserved for partners who'd previously botched a heist by sneezing into an alarm sensor. The plan was simple, elegant even. Bill would infiltrate as the entertainment, dazzling the seven-year-olds with balloon animals while she slipped through the back garden gate and loaded the loot into the getaway minivan, which she'd cleverly disguised with an ice cream decal. The cake's birthday boy, a tiny tyrant named Timmy, had reportedly received a deluxe robotics kit worth more than Molly's monthly rent. That alone justified the risk. "Remember," she hissed, "stay focused." Bill nodded solemnly, then immediately tripped over his enormous shoes, face-planting into a flowerbed. Molly closed her eyes and questioned every decision that had led her here.
created_at
"2026-05-29T10:08:06.704Z"
5/29/2026, 10:08:06 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2316
moderation_latency
(null)
generation_time
9625
tokens_prompt
77
tokens_completion
382
native_tokens_prompt
93
native_tokens_completion
556
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
0.014365
router
(null)
provider_responses
0
endpoint_id
"dfc0e5bd-d703-4fe2-a7bb-655eb95d5441"
id
"msg_01KfirSepYv4SK9VYPBm4MwP"
is_byok
false
latency
904
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-1780049286-hyGR3CkCfmCzPPqv8sKN"
session_id
(null)
api_type
"completions"
id
"gen-1780049286-cX0irR1itMDlFQUOPECa"
upstream_id
"msg_01KfirSepYv4SK9VYPBm4MwP"
total_cost
0.014365
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
86.79%
Dialogue to Total Word Ratio
Ratio: 3.86%, Deviation: 6.14%
neededClean
false
wordsTotal
207
wordsDialogue
8
93.2668%