NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXJ0C8MXVWBJDKA02HCS4G
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.9s
Cost:
$0.011865
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9920%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 spread the crayon-drawn map across the table, smoothing its wrinkled edges. "The objective is simple," she said. "We breach the perimeter during the piƱata distraction." Bill squinted at the diagram. "Why is the security guard wearing a clown nose?" "Because that's Bonkers the Clown, and he's the only thing standing between us and forty wrapped presents." "Forty?" Bill whistled. "What kind of kid gets forty presents?" "A spoiled one named Tyler whose father owns half the city." Molly tapped the map. "We go in through the bounce house." Bill leaned back, crossing his arms. "I don't do bounce houses. Last job, I sprained my dignity." "You'll bounce, and you'll like it." She slid him a juice box. "Hydrate. We're going to be there for hours." "What's our exit strategy?" "The ice cream truck. I bribed the driver with a kidney." Bill choked. "Whose kidney?" "Does it matter? Focus, Bill." She pointed at a stick figure. "This is the birthday boy. Avoid eye contact. Children sense fear." "And if someone asks who we are?" Molly grinned, pulling out two party hats. "We're entertainers. Now put this on and practice your balloon animals." Bill groaned. "I hate this job."
created_at
"2026-05-31T11:43:54.26Z"
5/31/2026, 11:43:54 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1185
moderation_latency
(null)
generation_time
8852
tokens_prompt
77
tokens_completion
321
native_tokens_prompt
93
native_tokens_completion
456
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
0.011865
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01XX3cyqMNaZNJmaawEZhPnK"
is_byok
false
latency
1185
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-1780227834-EMvgPe3ZQLEzVo3Jx6bH"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780227834-AiEfLOCEnu1guI1kmq1l"
upstream_id
"msg_01XX3cyqMNaZNJmaawEZhPnK"
total_cost
0.011865
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
198
0.00%
Dialogue to Total Word Ratio
Ratio: 72.36%, Deviation: 22.36%
neededClean
false
wordsTotal
199
wordsDialogue
144
49.9920%